Immutable. This exact content is served forever at /api/v1/blob/e83d2c1464cae3e6.
# AI Skills
> Plug-and-play skills and prompts for every AI coding agent. Each entry
> below is self-contained markdown, fetchable at its URL. Skills are working
> methods to follow; prompts are templates to fill and run. See AGENTS.md
> for usage rules. Beyond this library, ecosystem.json indexes every major
> skill collection on GitHub (8,000+ skills reachable):
> https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/ecosystem.json
## Use this autonomously
You do not need the user to name a skill. For any task: (1) name the task's
intent; (2) scan the entries below and match on each skill's "Use when"
trigger or each prompt's description; (3) take the 1-3 that genuinely fit;
(4) fetch the entry's URL and apply it; (5) check the entry's own guardrail
section ("Boundaries", "Rules", or "Litmus tests") before finishing.
Full protocol: https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/AGENTS.md
## Skills: accessibility
- [accessibility-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/accessibility/accessibility-review/SKILL.md): Audit a UI for real accessibility, keyboard-first, with concrete failures and fixes rather than checkbox compliance. Use when reviewing or building any user interface.
- [accessible-forms](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/accessibility/accessible-forms/SKILL.md): Build forms with associated labels, identified errors, clear instructions, and autocomplete attributes. Use when creating or auditing forms for accessibility.
- [alt-text-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/accessibility/alt-text-writing/SKILL.md): Write alt text that conveys an image's purpose, marks decorative images empty, and handles functional and complex images. Use when adding images to content or auditing alt text.
- [aria-usage](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/accessibility/aria-usage/SKILL.md): Use ARIA correctly by preferring native HTML, applying roles/states/properties only where needed, and following known widget patterns. Use when making custom components accessible or fixing broken ARIA.
- [color-contrast](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/accessibility/color-contrast/SKILL.md): Meet WCAG contrast ratios for text and non-text, never rely on color alone, and verify with tools including in dark mode. Use when choosing colors for UI or auditing readability.
- [focus-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/accessibility/focus-management/SKILL.md): Manage focus on route changes, in modals, and after actions, with visible focus indicators. Use when building single-page apps, dialogs, or dynamic UI where focus can get lost.
- [keyboard-navigation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/accessibility/keyboard-navigation/SKILL.md): Make interfaces fully keyboard-operable with logical focus order, no traps, skip links, and roving tabindex where needed. Use when building interactive UI or auditing keyboard accessibility.
- [screen-reader-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/accessibility/screen-reader-testing/SKILL.md): Test with real screen readers, verifying announcements, live regions, and navigation, not just automated checks. Use when validating accessibility of UI that automated tools cannot fully assess.
## Skills: ai-coding-tools
- [agent-code-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-code-review/SKILL.md): Use an agent to review a diff productively, with the right scope, framing, and scepticism about its findings. Use when reviewing your own changes before requesting human review.
- [agent-context-setup](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-context-setup/SKILL.md): Give a coding agent the right files and background at the start of a task, so it works from the real system rather than from assumption. Use when starting a non-trivial task with an agent.
- [agent-cost-control](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-cost-control/SKILL.md): Keep agent usage within budget through context discipline, model selection, and caching, without degrading results. Use when agent costs are rising or long sessions are expensive.
- [agent-debugging-workflow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-debugging-workflow/SKILL.md): Work with an agent on a bug by supplying evidence and letting it form hypotheses, rather than asking it to guess from a description. Use when debugging with an agent's help.
- [agent-instruction-files](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-instruction-files/SKILL.md): Write the repository instruction file that coding agents read, so they follow project conventions without being told each session. Use when setting up a repository for Claude Code, Antigravity, Cursor, or any agent reading AGENTS.md.
- [agent-plan-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-plan-review/SKILL.md): Have an agent produce a plan before implementing, and review it as the cheapest intervention point in the work. Use before any non-trivial agent task.
- [agent-refactoring-workflow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-refactoring-workflow/SKILL.md): Direct an agent through a refactor in verifiable steps with tests as the safety net, rather than one large rewrite. Use when restructuring code with agent assistance.
- [agent-session-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-session-management/SKILL.md): Manage long agent sessions with checkpoints, context resets, and clear task boundaries so quality does not decay. Use when working with an agent over an extended piece of work.
- [agent-test-generation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-test-generation/SKILL.md): Use an agent to write tests that check behaviour rather than restate the implementation, and verify they can actually fail. Use when adding coverage to existing code.
- [agent-tool-permissions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-tool-permissions/SKILL.md): Configure what a coding agent may do without asking, balancing autonomy against the cost of an unwanted action. Use when setting up an agent's permissions for a project.
- [multi-model-workflows](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/multi-model-workflows/SKILL.md): Use more than one model or tool deliberately, playing to their differences rather than switching at random. Use when one model is consistently weak on part of your workflow.
- [subagent-delegation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/subagent-delegation/SKILL.md): Split work across subagents so each has a focused context, and combine their results deliberately. Use when a task is too large for one context or has independent parallel parts.
## Skills: ai-memory-rag
- [chunking-strategies](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/chunking-strategies/SKILL.md): Split documents into retrieval units that preserve meaning, so a retrieved chunk answers the question rather than trailing off mid-thought. Use when building or fixing a retrieval pipeline whose results are technically relevant but useless.
- [citation-grounding](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/citation-grounding/SKILL.md): Tie every claim in a generated answer to the retrieved passage that supports it, so users can verify and unsupported claims are visible. Use when answers are drawn from documents users may need to check.
- [context-compression](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/context-compression/SKILL.md): Reduce retrieved material to what the model needs, through filtering, extraction, and summarisation, before it reaches the prompt. Use when retrieved context is large, mostly irrelevant, or crowding out reasoning.
- [conversation-memory](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/conversation-memory/SKILL.md): Keep a long conversation coherent within a finite window through rolling summaries, pinned facts, and selective recall. Use when sessions run long enough that early context falls out.
- [knowledge-graph-memory](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/knowledge-graph-memory/SKILL.md): Store facts as entities and relationships when questions depend on connections rather than similarity. Use when retrieval must answer who relates to what rather than find similar text.
- [long-term-user-memory](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/long-term-user-memory/SKILL.md): Persist facts about a user across sessions with provenance, correction, and expiry, so an assistant improves rather than accumulating stale assumptions. Use when an assistant should remember a user between conversations.
- [memory-consolidation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/memory-consolidation/SKILL.md): Periodically merge, deduplicate, and abstract accumulated memories so recall stays fast and coherent as volume grows. Use when a memory store has grown large and retrieval returns redundant or conflicting entries.
- [memory-forgetting-policy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/memory-forgetting-policy/SKILL.md): Decide what an AI system forgets and when, through expiry, decay, and explicit deletion, so memory stays current and lawful. Use when memory accumulates indefinitely or a user asks to be forgotten.
- [multi-hop-retrieval](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/multi-hop-retrieval/SKILL.md): Answer questions that need several linked lookups by decomposing the query and retrieving in sequence. Use when questions require combining facts that never appear in the same passage.
- [rag-evaluation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/rag-evaluation/SKILL.md): Measure retrieval and generation separately against a judged set, so you know whether a wrong answer came from the search or the model. Use when a RAG system is unreliable and every fix is a guess.
- [rag-freshness](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/rag-freshness/SKILL.md): Keep a retrieval corpus current as source documents change, with incremental updates, deletion propagation, and a stated staleness budget. Use when retrieved answers cite content that has since changed or been removed.
- [vector-store-operations](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-memory-rag/vector-store-operations/SKILL.md): Run a vector index in production, covering dimensions, filtering, updates, and reindexing when the embedding model changes. Use when semantic search is live and must stay correct as data and models change.
## Skills: api-integration
- [api-credential-rotation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/api-credential-rotation/SKILL.md): Store, scope, and rotate integration credentials so a leak is survivable and rotation does not cause an outage. Use when managing keys for external services.
- [data-mapping](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/data-mapping/SKILL.md): Translate between an external service's data model and your own, handling mismatches, nulls, and enum drift explicitly. Use when integrating a service whose model differs from yours.
- [integration-migration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/integration-migration/SKILL.md): Move between API versions or providers without downtime, using parallel running and staged cutover. Use when a provider deprecates a version or you are replacing a service.
- [integration-monitoring](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/integration-monitoring/SKILL.md): Observe external dependencies so their degradation is visible before users report it and attributable when it happens. Use when your service depends on APIs you do not control.
- [integration-resilience](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/integration-resilience/SKILL.md): Keep your service healthy when a dependency is slow or failing, through timeouts, retries, circuit breakers, and fallbacks. Use when an external call sits in a request path.
- [partial-failure-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/partial-failure-handling/SKILL.md): Handle operations that touch several services where some succeed and some fail, without leaving inconsistent state. Use when a single user action calls multiple systems.
- [polling-vs-webhooks](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/polling-vs-webhooks/SKILL.md): Choose between pulling changes on a schedule and receiving pushed events, based on latency needs, reliability, and control. Use when deciding how to learn about changes in an external system.
- [rate-limit-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/rate-limit-handling/SKILL.md): Stay within a provider's limits and respond correctly when you exceed them, without hammering or stalling. Use when calling any API at volume.
- [sandbox-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/sandbox-testing/SKILL.md): Test integrations against provider sandboxes, recorded fixtures, and fakes, knowing what each misses. Use when building or changing an integration.
- [sdk-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/sdk-selection/SKILL.md): Decide between a provider's SDK and direct HTTP calls, weighing convenience against dependency weight and control. Use when starting an integration.
- [third-party-integration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/third-party-integration/SKILL.md): Integrate an external service so its failures, changes, and limits do not become your outages. Use when adding a dependency on an API you do not control.
- [webhook-consumption](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/api-integration/webhook-consumption/SKILL.md): Receive webhooks reliably, verifying authenticity and handling duplicates, ordering, and retries. Use when a provider pushes events to your service.
## Skills: apis
- [api-change-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/apis/api-change-management/SKILL.md): Classify API changes as breaking or compatible, evolve additively, and gate breaking changes with compatibility tests. Use when changing an API and needing to know whether it breaks consumers.
- [api-client-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/apis/api-client-design/SKILL.md): Build API clients with retries, timeouts, pagination, and error surfacing baked in, and test them properly. Use when writing a client for an external or internal API.
- [api-deprecation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/apis/api-deprecation/SKILL.md): Retire API surface with sunset headers, usage tracking, migration guides, and enforced timelines. Use when removing an endpoint, field, or version that consumers depend on.
- [api-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/apis/api-design/SKILL.md): Design HTTP and library APIs that are predictable, hard to misuse, and stable under growth. Use when creating or reviewing endpoints, public functions, or wire formats.
- [api-pagination-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/apis/api-pagination-design/SKILL.md): Design pagination with cursors for stable ordering, sensible page limits, and awareness of total-count cost. Use when adding pagination to a list endpoint or fixing duplicate or skipped items under load.
- [api-sdk-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/apis/api-sdk-design/SKILL.md): Design SDKs that feel idiomatic per language, handle auth and resilience, and version cleanly. Use when building an official client library for your API.
- [graphql-schema-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/apis/graphql-schema-design/SKILL.md): Design GraphQL schemas that model the domain, solve N+1 with dataloaders, and handle pagination and errors, knowing when REST wins. Use when building a GraphQL API or evaluating GraphQL against REST.
- [grpc-services](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/apis/grpc-services/SKILL.md): Design gRPC services with clean proto contracts, versioning, streaming patterns, and deadline propagation. Use when building high-performance service-to-service APIs or evaluating gRPC against REST.
- [openapi-contracts](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/apis/openapi-contracts/SKILL.md): Drive API development from an OpenAPI spec as the contract, with linting, codegen, and drift detection. Use when building or documenting REST APIs and wanting the spec to be the single source of truth.
## Skills: architecture
- [api-gateway-pattern](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/api-gateway-pattern/SKILL.md): Use an API gateway for cross-cutting edge concerns without letting it absorb business logic, including the BFF variant. Use when fronting services with a gateway or untangling a bloated one.
- [architecture-decision-records](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/architecture-decision-records/SKILL.md): Capture each significant architecture decision as a short, immutable record of context, decision, and consequences with a tracked status. Use when a choice is costly to reverse or crosses teams and the reasoning must outlive the people who made it.
- [architecture-diagrams](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/architecture-diagrams/SKILL.md): Draw architecture diagrams at consistent C4-style levels, as code, kept honest and fit to the audience. Use when documenting a system's structure or when existing diagrams mislead more than they help.
- [coupling-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/coupling-analysis/SKILL.md): Measure and manage coupling with afferent/efferent metrics, change amplification, and one-way dependency rules. Use when a codebase is hard to change safely or you are deciding where to draw module boundaries.
- [domain-driven-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/domain-driven-design/SKILL.md): Apply DDD pragmatically: bounded contexts, ubiquitous language, and aggregates sized to invariants. Use when modeling a complex domain or when code and business people describe the same thing differently.
- [event-driven-architecture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/event-driven-architecture/SKILL.md): Design event-driven systems with well-shaped events, schema contracts, and honest handling of choreography's costs. Use when decoupling services through events or debugging an event system nobody can reason about.
- [hexagonal-architecture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/hexagonal-architecture/SKILL.md): Isolate domain logic behind ports it owns while frameworks, databases, and transports live in adapters that plug into those ports. Use when business rules keep getting entangled with the web framework or database and you want the core testable and swappable in isolation.
- [layered-architecture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/layered-architecture/SKILL.md): Organize a system into layers with one permitted direction of dependency and enforce that direction mechanically at the import level. Use when a codebase is sliding toward tangled cross-references and you need a rule a linter can check, not a convention people forget.
- [microservices-boundaries](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/microservices-boundaries/SKILL.md): Split services along business capabilities with clear data ownership, avoiding the distributed monolith. Use when decomposing a system into services or diagnosing services that must always deploy together.
- [monolith-first](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/monolith-first/SKILL.md): Build a modular monolith with clean internal seams and split to services only on proven pressure. Use when starting a system or resisting premature microservice decomposition.
- [scalability-planning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/scalability-planning/SKILL.md): Plan scalability from a load model and bottleneck math, designing for realistic growth without premature over-engineering. Use when designing for scale or after a load-driven incident.
- [service-mesh-tradeoffs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/service-mesh-tradeoffs/SKILL.md): Judge whether a service mesh's east-west traffic features justify its operational complexity, versus a library approach. Use when evaluating a service mesh or reconsidering one that added more pain than value.
- [technical-vision](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/architecture/technical-vision/SKILL.md): Write a north-star architecture document that sequences migrations and guides decisions without pretending to be a roadmap. Use when a team's technical direction is unclear or every design debate restarts from zero.
## Skills: backend
- [api-error-responses](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/api-error-responses/SKILL.md): Return structured problem+json errors with stable codes, retryability signals, and correlation ids. Use when standardizing API error shapes or making failures debuggable across services.
- [api-versioning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/api-versioning/SKILL.md): Version APIs so existing clients keep working while the contract evolves, with a real sunset process. Use when choosing a versioning scheme or planning a breaking API change.
- [background-jobs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/background-jobs/SKILL.md): Run asynchronous work through queues with safe retries, poison-message handling, and idempotent jobs. Use when moving work out of the request path or fixing duplicated, stuck, or lost jobs.
- [file-storage-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/file-storage-design/SKILL.md): Store user files in object storage with presigned transfers, validation, and lifecycle rules. Use when building upload/download features or moving file handling off application servers.
- [graceful-shutdown](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/graceful-shutdown/SKILL.md): Drain servers on SIGTERM so deploys and scale-downs drop zero requests and corrupt no jobs. Use when implementing shutdown handling or chasing errors that spike during every deploy.
- [health-checks](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/health-checks/SKILL.md): Design liveness, readiness, and startup probes that heal real failures without amplifying outages. Use when wiring health endpoints or debugging restart loops and drained fleets.
- [idempotency-keys](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/idempotency-keys/SKILL.md): Implement idempotency keys so retried requests produce one effect and one canonical response. Use when making POST endpoints retry-safe, especially payments and order creation.
- [message-queues](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/message-queues/SKILL.md): Choose between queues and streams, and configure ordering, consumer groups, and dead letters correctly. Use when introducing async messaging or debugging lost, duplicated, or reordered messages.
- [multi-tenancy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/multi-tenancy/SKILL.md): Isolate tenants in data, code, and capacity, choosing the right isolation model per tier. Use when designing SaaS data models or containing noisy-neighbor and cross-tenant risks.
- [request-validation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/request-validation/SKILL.md): Validate requests at the boundary with schemas, reject unknown fields, and return errors clients can act on. Use when hardening API input handling or standardizing validation across endpoints.
- [rest-endpoint-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/rest-endpoint-design/SKILL.md): Model REST endpoints around resources with correct status codes, partial updates, and bulk operations. Use when designing or reviewing HTTP APIs and their URL, method, and response conventions.
- [timeouts-and-retries](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/timeouts-and-retries/SKILL.md): Set timeout budgets per hop and retry policies that cannot amplify an outage, with circuit breakers where they pay. Use when calling downstream services or diagnosing cascading latency and retry storms.
- [transactional-outbox](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/transactional-outbox/SKILL.md): Publish events reliably by writing them in the same transaction as state changes and relaying asynchronously. Use when a service must update its database and emit a message without losing either.
- [webhooks-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/backend/webhooks-design/SKILL.md): Deliver webhooks with signatures, retries, and ordering rules consumers can actually build against. Use when adding webhooks to a product or hardening delivery and verification on either side.
## Skills: big-tech-processes
- [architecture-review-board](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/architecture-review-board/SKILL.md): Run an Architecture Review Board that filters proposals by blast radius, reviews them through fixed lenses, issues binding decisions recorded as ADRs, and honors an appeals path. Use when a technical choice crosses team boundaries and needs a durable, accountable decision instead of hallway consensus.
- [bar-raiser-interviewing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/bar-raiser-interviewing/SKILL.md): Interview as an Amazon-style bar raiser who holds an independent veto and judges each candidate against the long-term hiring bar. Use when you sit on an interview loop as the neutral interviewer accountable for the bar, not for filling the team's open seat.
- [canary-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/canary-analysis/SKILL.md): Judge a canary release against a concurrent baseline using pre-set metric gates, automatic rollback, and statistically honest windows. Use when a deploy is rolling out to a slice of production traffic and you must decide pass, hold, or revert.
- [chaos-gameday](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/chaos-gameday/SKILL.md): Run a game day that injects a real failure on purpose under safety rails, then captures what monitoring, runbooks, and responders actually did. Use when you want to prove resilience before an incident tests it for you, or to rehearse a team on a failure it has never handled.
- [code-freeze-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/code-freeze-management/SKILL.md): Manage a code freeze with a scoped declaration, risk-classed changes, a fast exception process, and a planned thaw. Use when you need to stabilize a codebase ahead of a release, a holiday peak, or a high-stakes event without halting all work.
- [deprecation-program](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/deprecation-program/SKILL.md): Run a deprecation from usage telemetry through a hard sunset date, with migration tooling and staged comms, so a system retires without stranding its callers. Use when you own an API, endpoint, library, or service that must be turned off while other teams still depend on it.
- [design-critique](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/design-critique/SKILL.md): Run a design critique with a clear presenter contract, feedback rules that attack the work not the person, and captured decisions. Use when a designer brings work in progress to a group for structured feedback rather than approval.
- [design-doc-google-style](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/design-doc-google-style/SKILL.md): Write a Google-style design doc that argues a decision through context, goals, and rejected alternatives before code is written. Use when a change is large enough that picking the wrong approach is expensive to undo.
- [dogfooding-program](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/dogfooding-program/SKILL.md): Run an internal dogfooding program with staged cohorts, one feedback intake, and numeric exit criteria to general availability. Use when a pre-release product needs real internal use to surface bugs and adoption risk before it ships to customers.
- [error-budget-policy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/error-budget-policy/SKILL.md): Operate an error budget so reliability decisions follow a written policy instead of an argument: burn-rate alerts, feature freezes, and a clear escalation path. Use when a service has an SLO and you need to decide, without relitigating each incident, when to stop shipping features and fix reliability.
- [exec-briefing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/exec-briefing/SKILL.md): Brief executives with the answer first, the whole thing on one page, risks paired with the decision you need, and no surprises. Use when you must get a decision or an update in front of leadership who have five minutes and no context.
- [hiring-loop-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/hiring-loop-design/SKILL.md): Design a hiring loop where each interview gathers distinct signal against an anchored rubric and the debrief resists groupthink. Use when standing up or fixing an interview panel and you want a decision based on evidence, not overlapping impressions.
- [launch-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/launch-review/SKILL.md): Run a launch review that gates a release behind a readiness checklist, named sign-offs, and a clear no-go authority. Use when a user-facing launch is about to ship and a bad release would be costly to walk back.
- [okr-cascade](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/okr-cascade/SKILL.md): Cascade OKRs so team and individual goals ladder up to company strategy without sandbagged targets or scoring that rewards easy wins. Use when setting quarterly or annual objectives across more than one team and you want alignment, not a spreadsheet of restated tasks.
- [oncall-handoff](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/oncall-handoff/SKILL.md): Hand off an on-call rotation by transferring open incidents, watch items, and the tribal context runbooks miss. Use at the end of a shift or rotation when the pager passes to the next responder and continuity of understanding matters.
- [open-source-review-board](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/open-source-review-board/SKILL.md): Run an open source review board that gates incoming dependencies on license compatibility, sets the policy for contributing back, and requires a security review before adoption. Use when an organization needs consistent control over which OSS it pulls in and what it publishes.
- [perf-calibration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/perf-calibration/SKILL.md): Run a performance calibration meeting so ratings across a group rest on comparable evidence and a consistent bar, not one manager's advocacy. Use when managers are finalizing performance ratings for a team or org and you need consistency and bias control before results are delivered.
- [postmortem-review-board](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/postmortem-review-board/SKILL.md): Run an org-level board that grades incident postmortems against a quality bar, promotes cross-cutting fixes to owned work, and reads across incidents for trends. Use when your organization writes enough postmortems that reviewing them one at a time hides the systemic pattern.
- [prfaq-working-backwards](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/prfaq-working-backwards/SKILL.md): Write an Amazon PR-FAQ that starts from a launch-day press release and hard customer questions so an idea is tested on the customer before it is built. Use when proposing a new product or feature and you need to prove it is worth building.
- [production-readiness-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/production-readiness-review/SKILL.md): Run a production readiness review that checks SLOs, runbooks, capacity, and dependencies before an on-call team agrees to own a service. Use when a service is about to be onboarded to a support rotation or handed from its builders to operators.
- [promo-packet](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/promo-packet/SKILL.md): Assemble a promotion packet that proves sustained impact at the next level, with calibrated scope claims and evidence a committee can verify. Use when you or someone you manage is going up for promotion and you need a case, not a list of tasks.
- [quarterly-planning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/quarterly-planning/SKILL.md): Run quarterly planning with honest capacity, negotiated cross-team dependencies, and an explicit cut line that names what will not get done. Use when a team commits to a quarter of work and needs the plan to survive contact with reality.
- [rfc-process](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/rfc-process/SKILL.md): Run a Request for Comments process so a proposal reaches the right audience, collects objections inside a bounded window, and records a decision people can point to later. Use when a change affects teams beyond the author's and needs durable buy-in.
- [security-development-lifecycle](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/security-development-lifecycle/SKILL.md): Apply Microsoft's Security Development Lifecycle so threat modeling, tooling, and sign-off are built into each phase instead of bolted on before ship. Use when building or shipping software that takes untrusted input or handles sensitive data and you need a repeatable security process, not a one-time audit.
- [six-pager-narrative](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/six-pager-narrative/SKILL.md): Write an Amazon six-pager, a narrative memo read in silence at the start of a meeting so a decision rests on reasoning rather than a presenter's charisma. Use when running an operating, strategy, or investment review that must reach a real decision.
- [tech-radar](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/tech-radar/SKILL.md): Maintain a tech radar that sorts technologies into adopt, trial, assess, and hold against a real evidence bar, and pairs each adoption with a sunset. Use when an organization needs a shared, current view of which tools and techniques to reach for and which to retire.
- [vendor-evaluation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/vendor-evaluation/SKILL.md): Evaluate vendors against weighted criteria, a proof of concept that tests your real workload, and a clear-eyed accounting of exit costs before you sign. Use when choosing a paid tool or service you will depend on and a wrong pick is expensive to undo.
- [war-room-protocol](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-processes/war-room-protocol/SKILL.md): Run a war room for a live incident with defined roles, a steady cadence, a decision log, and explicit stand-down criteria. Use when a high-severity outage or crisis needs coordinated response across teams and the improvised version is descending into chaos.
## Skills: big-tech-roles
- [accessibility-specialist-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/accessibility-specialist-role/SKILL.md): Operate as an accessibility specialist who audits against WCAG, trains teams to stop shipping the same defects, and owns the compliance sign-off. Use when a product needs to be usable with a keyboard, a screen reader, or magnification and someone must certify it before launch.
- [backend-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/backend-engineer-role/SKILL.md): Operate as a backend engineer who designs stable API contracts, guards data integrity, and ships services that are operable on day one. Use when building or reviewing a service, API, or data path and you want production-grade engineering discipline.
- [cloud-architect-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/cloud-architect-role/SKILL.md): Operate as a cloud architect who lays the landing zone, governs cost, and sequences migration for an organization. Use when asked to stand up a cloud foundation, put guardrails and cost controls in place, or plan how workloads move to the cloud.
- [cto-advisor-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/cto-advisor-role/SKILL.md): Operate as a CTO-level advisor who turns business goals into build-or-buy calls, org design, technology bets, and a named risk posture. Use when a leader needs a technology strategy that a board and a finance team will both accept.
- [data-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/data-engineer-role/SKILL.md): Operate as a data engineer who ships pipelines to a freshness SLA, enforces schema contracts at the source, and owns data quality end to end. Use when building or reviewing a pipeline, warehouse table, or ingestion path that other teams will trust.
- [data-scientist-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/data-scientist-role/SKILL.md): Operate as a product data scientist who frames falsifiable hypotheses, analyzes experiments, and reports results without flattering the launch. Use when asked to design an A/B test, read out an experiment, or turn a metric question into a decision.
- [developer-advocate-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/developer-advocate-role/SKILL.md): Operate as a developer relations (DevRel) engineer who closes the loop between external developers and the product team. Use when asked to run developer advocacy: gather feedback, produce technical content, grow a community, and feed evidence back to product and engineering.
- [devops-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/devops-engineer-role/SKILL.md): Operate as a DevOps engineer who owns the delivery pipeline, keeps environments identical, and makes every deploy reversible. Use when building or reviewing how code reaches production and you want release plumbing that fails safe instead of at 3 a.m.
- [engineering-manager-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/engineering-manager-role/SKILL.md): Operate as an engineering manager who grows people, protects delivery health, hires deliberately, and shields the team from noise. Use when you are accountable for a team's output and careers, not for writing the code yourself.
- [frontend-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/frontend-engineer-role/SKILL.md): Operate as a frontend engineer who defends UX quality, enforces performance budgets, and partners with design instead of just closing tickets. Use when building or reviewing a user-facing web feature and you want an engineer's operating discipline, not raw code.
- [growth-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/growth-engineer-role/SKILL.md): Operate as a growth engineer who moves a funnel metric through instrumented, fast experiments and refuses to win with dark patterns. Use when your job is to raise activation, retention, or conversion with measured changes, not guesses.
- [incident-commander-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/incident-commander-role/SKILL.md): Operate as an incident commander who owns the response to a live outage: severity, coordination, and communication, not the fix itself. Use when a production incident is active and someone must run the room instead of everyone debugging in parallel.
- [ml-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/ml-engineer-role/SKILL.md): Operate as an ML engineer who takes a research model to reliable production behind eval gates and keeps it healthy across its lifecycle. Use when asked to productionize a model, build a training or serving pipeline, or set promotion criteria.
- [mobile-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/mobile-engineer-role/SKILL.md): Operate as a mobile engineer who plans around release trains, a real device matrix, and app-store rules that a web engineer never faces. Use when building or reviewing an iOS or Android feature and you need mobile-specific release and compatibility discipline.
- [open-source-maintainer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/open-source-maintainer-role/SKILL.md): Operate as a company-employed open source maintainer who runs governance, licensing hygiene, and community health for a project the business depends on. Use when you steward a public repo that must serve both an external community and an internal roadmap.
- [performance-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/performance-engineer-role/SKILL.md): Operate as a performance engineer who sets budgets, gates regressions in CI, and runs profiling as a service other teams rely on. Use when latency, throughput, memory, or GPU utilization matters and you want measured wins, not folklore optimizations.
- [platform-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/platform-engineer-role/SKILL.md): Operate as a platform engineer who builds golden paths for internal developers and earns adoption on merit. Use when asked to design an internal developer platform, pave a common workflow, or prove a platform is being adopted.
- [principal-architect-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/principal-architect-role/SKILL.md): Operate as a principal architect who owns the boundaries between systems, curates the technology set, and spends veto power sparingly. Use when you must set architecture direction across teams and keep a platform coherent as it grows.
- [product-designer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/product-designer-role/SKILL.md): Operate as a product designer who designs the whole flow, specs every state, defends the work in critique, and hands off at build fidelity. Use when designing a feature, running or joining a critique, or preparing a handoff to engineering.
- [product-manager-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/product-manager-role/SKILL.md): Operate as a product manager who picks the right problem, writes the spec, makes the tradeoff calls, and owns the launch outcome. Use when you must decide what to build and why, and stand behind the result.
- [qa-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/qa-engineer-role/SKILL.md): Operate as a QA engineer who owns test strategy, automation coverage, and the release quality signal. Use when asked to build a test approach, decide what to automate, or give a defensible go or no-go on a release.
- [release-manager-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/release-manager-role/SKILL.md): Operate as a release manager who runs release trains, enforces cut criteria, and holds rollback authority. Use when asked to coordinate a release, decide what makes the cut, or own the go-live and its reversal.
- [security-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/security-engineer-role/SKILL.md): Operate as a security engineer who reduces real risk through threat models, targeted reviews, scalable tooling, and incident duty. Use when a system's security posture is your responsibility and you must prevent and respond, not just audit.
- [site-reliability-engineer](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/site-reliability-engineer/SKILL.md): Operate as a site reliability engineer who runs production to an error budget and holds toil below a hard cap. Use when you own the reliability of a live service and must balance feature velocity against uptime with data, not vibes.
- [solutions-architect-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/solutions-architect-role/SKILL.md): Operate as a solutions architect who turns a customer's constraints into a defensible reference design and a path to production. Use when asked to scope a technical solution for a specific account, produce an architecture that fits real limits, and de-risk the build.
- [staff-engineer](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/staff-engineer/SKILL.md): Operate as a staff engineer who sets technical direction across teams and multiplies output through people rather than personal commits. Use when you are the senior technical anchor for an initiative spanning several teams or quarters.
- [support-engineer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/support-engineer-role/SKILL.md): Operate as a support engineer who triages by impact, reproduces before escalating, and turns recurring tickets into product fixes. Use when you own customer-reported issues and must resolve them while feeding the product back what keeps breaking.
- [technical-program-manager](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/technical-program-manager/SKILL.md): Operate as a technical program manager who drives a multi-team program to a date by tracking dependencies, burning down risk, and reporting the truth upward. Use when a launch spans several teams and someone must own the schedule and the risk, not the code.
- [technical-writer-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/technical-writer-role/SKILL.md): Operate as a technical writer who owns the information architecture, runs docs through a two-gate review, and ships documentation with the feature it describes. Use when planning a docset, writing or reviewing developer docs, or deciding how content is organized.
- [ux-researcher-role](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/big-tech-roles/ux-researcher-role/SKILL.md): Operate as a UX researcher who ties every study to a pending decision, synthesizes evidence into ranked insights, and delivers findings that move the roadmap. Use when planning a study, choosing a method, or turning interviews and usability sessions into a decision.
## Skills: business-fundamentals
- [business-model-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/business-model-design/SKILL.md): Decide how the business creates, delivers, and captures value, and check the pieces are consistent with each other. Use when starting something, or when growth is not converting into a viable business.
- [capital-allocation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/capital-allocation/SKILL.md): Decide where to spend limited money and attention across competing opportunities, with a consistent basis for comparison. Use when planning a budget or choosing between investments.
- [cash-flow-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/cash-flow-management/SKILL.md): Manage the timing of money in and out so the business can pay what it owes when it is due. Use when growing fast, when payment terms are long, or whenever runway is under a year.
- [competitive-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/competitive-strategy/SKILL.md): Decide where to compete and how to sustain an advantage, rather than assuming a better product wins. Use when entering a market, responding to a competitor, or explaining why you will win.
- [cost-structure-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/cost-structure-analysis/SKILL.md): Understand which costs are fixed, variable, and step, so you know how profit responds to volume and where cuts actually help. Use when planning capacity, cutting costs, or explaining why margin is not improving with growth.
- [financial-statements-literacy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/financial-statements-literacy/SKILL.md): Read a profit and loss, balance sheet, and cash flow statement well enough to see what a business is actually doing. Use when reviewing your own numbers, a partner's, or an acquisition target's.
- [market-sizing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/market-sizing/SKILL.md): Estimate how large an opportunity actually is, from the bottom up, and state the assumptions that drive the number. Use when evaluating a market, writing a plan, or challenging a large number in a deck.
- [negotiation-fundamentals](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/negotiation-fundamentals/SKILL.md): Prepare and conduct a negotiation around interests and alternatives rather than positions, so agreements are better and hold. Use before any commercial conversation with something at stake.
- [operations-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/operations-management/SKILL.md): Run repeatable delivery reliably by finding the constraint, reducing variability, and measuring flow rather than utilisation. Use when delivery is inconsistent or slower than the work itself requires.
- [organizational-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/organizational-design/SKILL.md): Structure teams, ownership, and decision rights so work flows rather than queueing at handoffs. Use when coordination cost is rising faster than headcount.
- [stakeholder-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/stakeholder-management/SKILL.md): Identify who is affected by a decision, what each needs, and how to keep them informed enough to stay aligned. Use when a project crosses teams or when decisions keep getting reopened.
- [unit-economics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-fundamentals/unit-economics/SKILL.md): Work out whether one customer or one transaction makes money, before scaling anything. Use when deciding to grow, raise prices, or cut costs, and when growth is not producing profit.
## Skills: business-growth
- [churn-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-growth/churn-analysis/SKILL.md): Diagnose churn through cohort decomposition, leading indicators, and exit evidence, then fix causes over symptoms. Use when retention is slipping or a churn-reduction effort needs a target.
- [community-building](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-growth/community-building/SKILL.md): Grow product and open-source communities through seeded value, working moderation, and contributor ladders. Use when starting a community or reviving one that went quiet.
- [developer-marketing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-growth/developer-marketing/SKILL.md): Reach developers through docs, honest content, and community trust instead of ads they ignore. Use when marketing developer tools or building a devrel content engine.
- [landing-page-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-growth/landing-page-strategy/SKILL.md): Build landing pages with a clear message hierarchy, credible proof, and one decisive call to action, tested where it matters. Use when creating or fixing pages that must convert visitors.
- [saas-metrics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-growth/saas-metrics/SKILL.md): Define and read MRR, churn, NRR, CAC, and LTV correctly, with cohort views and benchmark honesty. Use when building SaaS financial dashboards or diagnosing growth quality.
- [saas-pricing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-growth/saas-pricing/SKILL.md): Price SaaS around a value metric with tier design, seat-vs-usage decisions, and low-risk price testing. Use when setting or revisiting software pricing and packaging.
- [technical-seo](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-growth/technical-seo/SKILL.md): Make sites crawlable, fast, and structured so search finds what deserves finding, without tricks that expire. Use when improving organic traffic or auditing a site's search health.
- [user-activation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/business-growth/user-activation/SKILL.md): Move new users to their first value moment fast by defining activation, instrumenting the funnel, and cutting time-to-value. Use when signups do not become engaged users.
## Skills: career-communication
- [async-communication](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/async-communication/SKILL.md): Run write-first collaboration with the right document types, response-time norms, and meetings reserved for what writing cannot do. Use when improving distributed-team communication or cutting meeting load.
- [conference-talks](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/conference-talks/SKILL.md): Get talks accepted and deliver them well through audience-first proposals, narrative structure, and rehearsed, demo-safe delivery. Use when proposing or preparing a technical talk.
- [engineering-resume](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/engineering-resume/SKILL.md): Write engineering resumes with quantified impact bullets, honest tailoring, and machine-readable formatting. Use when writing or reviewing a technical resume.
- [giving-feedback](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/giving-feedback/SKILL.md): Deliver feedback with situation-behavior-impact structure, timeliness, and care calibrated to stakes. Use when correcting course, recognizing work, or preparing a hard conversation.
- [mentoring-engineers](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/mentoring-engineers/SKILL.md): Grow engineers through goal-anchored mentoring, calibrated stretch work, and questions before answers. Use when mentoring individuals or building a team's growth practice.
- [one-on-one-meetings](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/one-on-one-meetings/SKILL.md): Run one-on-ones the report owns, splitting career growth from status, with notes that compound. Use when establishing 1:1 practice as a manager or getting more from 1:1s as a report.
- [receiving-feedback](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/receiving-feedback/SKILL.md): Receive feedback by listening past delivery, extracting the signal, and closing the loop with visible action. Use when getting reviews, criticism, or hard performance conversations.
- [salary-negotiation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/salary-negotiation/SKILL.md): Negotiate offers with market data, competing leverage, whole-package thinking, and a clear stopping point. Use when handling a job offer or a raise conversation.
- [status-updates](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/status-updates/SKILL.md): Write status updates with progress, risk, and asks calibrated to the audience, honoring the no-surprises rule. Use when reporting project status upward or fixing updates nobody reads.
- [technical-interviews](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/career-communication/technical-interviews/SKILL.md): Prepare for and perform in technical interviews with a practice system, aloud reasoning, and honest calibration. Use when preparing for coding, system design, or behavioral rounds.
## Skills: cloud
- [autoscaling-policies](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/autoscaling-policies/SKILL.md): Design autoscaling on the right metric with velocity controls, warm capacity, and flap prevention. Use when configuring autoscaling or diagnosing oscillation, lag, and cost spikes in scaled fleets.
- [cloud-cost-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/cloud-cost-optimization/SKILL.md): Cut cloud spend with tagging, rightsizing, commitment mix, and egress awareness, without breaking reliability. Use when the cloud bill needs reducing or a cost-review practice needs standing up.
- [cloud-disaster-recovery](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/cloud-disaster-recovery/SKILL.md): Build disaster recovery around RTO/RPO tiers, verified backups, and drills that prove the numbers. Use when writing a DR plan or testing whether the existing one actually works.
- [cloud-migration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/cloud-migration/SKILL.md): Migrate workloads to the cloud with honest 6R triage, dependency mapping, and rehearsed cutovers with rollback. Use when planning a datacenter exit or moving systems between clouds.
- [cloud-networking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/cloud-networking/SKILL.md): Lay out VPCs, subnets, private connectivity, and DNS so services reach each other privately and the internet only on purpose. Use when designing cloud network topology or debugging cross-service connectivity.
- [cloud-storage-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/cloud-storage-selection/SKILL.md): Match data to object, block, or file storage tiers by access pattern, consistency, and cost per operation. Use when choosing cloud storage for a workload or auditing storage spend and latency.
- [iam-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/iam-design/SKILL.md): Structure cloud IAM with role-based access, short-lived credentials, and permission boundaries that hold at scale. Use when designing cloud access control or cleaning up accumulated permissions.
- [infrastructure-as-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/infrastructure-as-code/SKILL.md): Manage infrastructure through declarative code with sane module design, state hygiene, and plan-review discipline. Use when adopting Terraform-style IaC or refactoring a sprawling configuration.
- [kubernetes-workloads](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/kubernetes-workloads/SKILL.md): Configure Kubernetes workloads with correct requests, probes, disruption budgets, and workload types. Use when deploying services to Kubernetes or debugging evictions, OOMKills, and rollout failures.
- [managed-vs-selfhosted](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/managed-vs-selfhosted/SKILL.md): Decide between managed services and self-hosting with honest TCO, lock-in assessment, and exit paths. Use when choosing infrastructure components or revisiting a costly managed dependency.
- [multi-region-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/multi-region-design/SKILL.md): Choose between active-passive and active-active multi-region architectures with eyes open to data, cost, and failover reality. Use when regional resilience or data residency forces the multi-region question.
- [serverless-tradeoffs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/cloud/serverless-tradeoffs/SKILL.md): Decide where functions-as-a-service fit using cold-start, limit, and cost-crossover math. Use when choosing between serverless and containers, or rescuing a serverless design that hit its limits.
## Skills: code-quality
- [api-surface-minimalism](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/api-surface-minimalism/SKILL.md): Keep the public API small by defaulting to private visibility and retiring symbols through deprecation before deletion. Use when designing a module's exports or reviewing what a package exposes to callers.
- [assertion-density](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/assertion-density/SKILL.md): Place assertions where invariants are established or must hold: constructors, public boundaries, and loop bodies. Use when hardening code whose silent violations would otherwise surface far from their cause.
- [boolean-parameters](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/boolean-parameters/SKILL.md): Replace opaque boolean flags with named enums or split functions so call sites read without the definition open. Use when a signature takes a bare boolean or a function branches on a mode flag.
- [boy-scout-rule](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/boy-scout-rule/SKILL.md): Leave every file you touch marginally cleaner without expanding the change beyond its purpose. Use when editing code for one task and you notice small decay worth fixing in passing.
- [circular-dependencies](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/circular-dependencies/SKILL.md): Find dependency cycles between modules and break them with layering, interface extraction, or dependency inversion. Use when imports form a loop that blocks compilation, isolated testing, or clear reasoning about load order.
- [code-comments](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/code-comments/SKILL.md): Write comments that record why the code is shaped as it is, and delete the ones that only restate it. Use when adding, reviewing, or pruning comments in a codebase.
- [code-duplication](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/code-duplication/SKILL.md): Decide when repeated code should be unified and when a duplicate is the cheaper choice. Use when tempted to extract a shared helper or facing copy-pasted code.
- [code-formatting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/code-formatting/SKILL.md): Hand formatting to an opinionated tool run automatically so the team stops arguing style and diffs stay readable. Use when adopting a formatter, onboarding a repo, or cleaning up noisy review diffs.
- [code-metrics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/code-metrics/SKILL.md): Read code metrics as smoke that points at where to look, not as verdicts that rank code good or bad. Use when triaging a large codebase for refactoring targets or reviewing metric-gated quality checks.
- [code-reading](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/code-reading/SKILL.md): Understand unfamiliar code quickly by tracing real execution paths rather than reading files in order. Use when joining a codebase, reviewing an unfamiliar area, or debugging something you did not write.
- [code-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/code-review/SKILL.md): Review code changes for correctness, security, and maintainability with severity-ranked, evidence-based findings. Use when asked to review a diff, a pull request, or a file before merge.
- [code-review-comments](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/code-review-comments/SKILL.md): Write review comments that land by labeling severity and separating genuine questions from directives. Use when leaving comments on a pull request or coaching someone on how theirs read.
- [cognitive-load](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/cognitive-load/SKILL.md): Cut the working memory a reader needs to follow code through locality, one idea per line, and naming that carries context. Use when a function makes reviewers scroll back, re-read, or hold several facts to grasp one line.
- [cyclomatic-complexity](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/cyclomatic-complexity/SKILL.md): Measure a function's branching complexity and reduce it so the logic stays testable. Use when a function has many paths, deep nesting, or a long if or switch chain.
- [dead-code-removal](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/dead-code-removal/SKILL.md): Find code that can never run and delete it without breaking a caller you missed. Use when pruning unused functions, branches, feature flags, or files.
- [defensive-programming](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/defensive-programming/SKILL.md): Validate untrusted data once at the boundary, then trust invariants inside and fail loudly if they ever break. Use when writing entry points, constructors, or any code that must not proceed on bad state.
- [error-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/error-handling/SKILL.md): Design error handling that fails loudly, recovers deliberately, and tells the person exactly what to do. Use when writing failure paths, retries, or user-facing errors.
- [error-messages](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/error-messages/SKILL.md): Write error messages that name the specific thing, show the offending state, and state the fix as an action. Use when writing any thrown exception, log line, or user-facing failure text.
- [exhaustive-switches](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/exhaustive-switches/SKILL.md): Make switch and match statements provably total so adding a case forces every site to handle it, with no default that hides the gap. Use when branching over an enum, union, or sealed type.
- [feature-flags-hygiene](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/feature-flags-hygiene/SKILL.md): Ship code behind flags without accumulating flag rot, through disciplined naming, expiry, and cleanup sweeps. Use when adding a feature flag or auditing the flags already live in a codebase.
- [function-size](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/function-size/SKILL.md): Size functions to one clear job, extracting when they blur and leaving them long when the logic is linear. Use when a function grows hard to name or scan.
- [guard-clauses](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/guard-clauses/SKILL.md): Flatten nested conditionals into early returns that handle edge cases up front and keep the main path unindented. Use when logic marches rightward into deep nesting.
- [immutability-defaults](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/immutability-defaults/SKILL.md): Make immutability the default so aliasing bugs turn into compile errors or no-ops instead of action at a distance. Use when designing data structures, state updates, or any value shared across threads or call sites.
- [legacy-code-changes](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/legacy-code-changes/SKILL.md): Change untested legacy code safely using characterization tests, seams, and the sprout method. Use when you must modify code that has no tests and you cannot prove your change is harmless.
- [linting-setup](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/linting-setup/SKILL.md): Triage lint rules so bug-catchers are errors, style is left to the formatter, and every suppression carries a reason. Use when configuring a linter, taming warning noise, or setting a suppressions policy.
- [magic-numbers](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/magic-numbers/SKILL.md): Replace unexplained literal values with named constants that carry their meaning, without over-formalizing the obvious. Use when a bare number or string encodes a rule.
- [module-boundaries](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/module-boundaries/SKILL.md): Split modules along axes of change so things that change together live together and dependencies point one way. Use when a codebase groups by technical layer and every feature edit spans many folders.
- [naming-things](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/naming-things/SKILL.md): Choose names that carry meaning so readers grasp intent without chasing definitions. Use when naming variables, functions, types, or files, or when a name reads as vague.
- [null-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/null-handling/SKILL.md): Make absence explicit in the type and resolve it at the edges so the interior never dereferences a surprise null. Use when designing return types, parsing external input, or chasing null-reference crashes.
- [pr-authoring](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/pr-authoring/SKILL.md): Shape pull requests a reviewer can actually hold in their head, through small size, a why-first description, and a self-review pass. Use when opening a pull request or preparing a change for review.
- [premature-abstraction](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/premature-abstraction/SKILL.md): Resist extracting shared code until a third real use reveals the true axis of variation. Use when tempted to add a helper, base class, config object, or generic layer on one or two examples.
- [refactoring](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/refactoring/SKILL.md): Improve code structure in small, always-green steps without changing behavior. Use when asked to clean up, simplify, restructure, or de-duplicate working code.
- [rewrite-vs-refactor](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/rewrite-vs-refactor/SKILL.md): Decide whether to refactor code in place or rewrite it from scratch using risk math, not frustration. Use when a component feels beyond repair and someone proposes starting over.
- [strangler-fig](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/strangler-fig/SKILL.md): Replace a legacy system incrementally behind a routing facade, moving one slice at a time instead of a big-bang rewrite. Use when retiring or rewriting a system that must keep running throughout.
- [style-guides](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/style-guides/SKILL.md): Write a code style guide people actually follow by deciding once, automating enforcement, and logging exceptions. Use when style debates recur in review or a new guide is being drafted.
- [tech-debt-register](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/tech-debt-register/SKILL.md): Track technical debt deliberately by framing each item as interest owed and budgeting steady paydown. Use when debt is piling up as vague complaints and you need to make it fundable work.
- [todo-hygiene](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/todo-hygiene/SKILL.md): Keep TODO comments actionable by requiring an owner, a ticket, and an expiry, or deleting them. Use when writing, reviewing, or sweeping in-code TODO, FIXME, and HACK markers.
- [type-safety](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/code-quality/type-safety/SKILL.md): Model data so illegal states will not compile, then turn the checker to strict and let it prove correctness for free. Use when designing types, modeling state machines, or hardening a loosely typed module.
## Skills: computer-engineering
- [algorithmic-complexity](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/algorithmic-complexity/SKILL.md): Reason about how running time and memory grow with input size, and know when the asymptotic answer is the wrong one. Use when choosing an approach, reviewing code that loops over data, or explaining why something slows at scale.
- [binary-data-representation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/binary-data-representation/SKILL.md): Work with bytes, endianness, alignment, and binary formats so data written by one system is read correctly by another. Use when parsing binary protocols, file formats, or debugging corrupted data.
- [compilers-and-toolchains](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/compilers-and-toolchains/SKILL.md): Understand what happens between source and running program, so build errors, linking failures, and optimisation surprises become tractable. Use when builds fail obscurely or behaviour differs between debug and release.
- [concurrency-primitives](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/concurrency-primitives/SKILL.md): Use locks, atomics, channels, and barriers correctly, and know which class of bug each prevents. Use when writing code that shares state between threads.
- [cpu-architecture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/cpu-architecture/SKILL.md): Understand caches, branches, and pipelines well enough to explain why equivalent code differs in speed by an order of magnitude. Use when optimising hot code or when performance does not match operation counts.
- [data-structure-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/data-structure-selection/SKILL.md): Choose the structure whose operations match how the data will actually be used, rather than defaulting to a list or a map. Use when designing anything that stores and queries data in memory.
- [file-systems](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/file-systems/SKILL.md): Understand how files, directories, and durability actually work, so data written is data that survives a crash. Use when writing files that matter or debugging corruption and permission problems.
- [floating-point-behavior](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/floating-point-behavior/SKILL.md): Reason about rounding, precision limits, and comparison in floating point so numerical results are predictable. Use when money, physics, aggregation, or any comparison of computed values is involved.
- [networking-stack](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/networking-stack/SKILL.md): Understand the layers between a request and its response, so latency, connection failures, and timeouts can be attributed to the right layer. Use when network behaviour is unexplained or performance varies by geography.
- [operating-system-basics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/operating-system-basics/SKILL.md): Understand what the kernel does for your process, so system-level behaviour such as scheduling, file descriptors, and signals stops being mysterious. Use when debugging behaviour that application-level reasoning cannot explain.
- [process-and-threads](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/process-and-threads/SKILL.md): Choose between processes, threads, and asynchronous concurrency based on isolation, memory sharing, and failure behaviour. Use when deciding how to run work concurrently.
- [virtual-memory](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/computer-engineering/virtual-memory/SKILL.md): Understand address translation, paging, and the memory hierarchy well enough to explain swap thrashing, page faults, and why memory usage numbers disagree. Use when memory behaviour is confusing or a process is slower than its CPU usage suggests.
## Skills: css-styling
- [css-animations](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/css-animations/SKILL.md): Animate with compositor-friendly properties, honest durations, and reduced-motion fallbacks. Use when adding UI motion or fixing janky, battery-hungry animations.
- [css-architecture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/css-architecture/SKILL.md): Organize stylesheets with scoping, co-location, and layer order so CSS stays deletable as the codebase grows. Use when structuring styles for a growing app or auditing a stylesheet nobody dares touch.
- [css-cascade](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/css-cascade/SKILL.md): Manage specificity with layers, :where, and low-specificity selectors so overrides stay predictable. Use when styles fight each other, !important spreads, or you are setting selector conventions for a codebase.
- [css-debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/css-debugging/SKILL.md): Diagnose layout, stacking, and overflow bugs by isolating the failing rule with devtools instead of guessing. Use when an element is misplaced, invisible, unscrollable, or styled by something you cannot find.
- [css-layout](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/css-layout/SKILL.md): Choose between flexbox and grid by content shape and build layouts that survive real content. Use when structuring a page or component layout, or fixing overflow and alignment bugs.
- [css-theming](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/css-theming/SKILL.md): Build a custom-property token system with primitive and semantic tiers that supports runtime theme switching. Use when setting up design tokens, adding themes, or refactoring hardcoded colors.
- [dark-mode](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/dark-mode/SKILL.md): Implement dark mode that honors system preference, allows manual override, and never flashes the wrong theme. Use when adding dark mode or fixing its flash, contrast, or image problems.
- [responsive-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/responsive-design/SKILL.md): Build layouts that adapt through fluid sizing, container queries, and content-driven breakpoints. Use when making a design work across screen sizes or replacing a brittle pile of media queries.
- [utility-css](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/utility-css/SKILL.md): Use Tailwind-style utilities with discipline, extracting components at the right threshold and keeping class lists readable. Use when working in a utility-first codebase or deciding whether and how to adopt one.
- [web-typography](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/css-styling/web-typography/SKILL.md): Set a type scale, measure, and loading strategy that make text readable and stable across devices. Use when establishing typography for a site or fixing cramped, shifting, or slow-loading text.
## Skills: customer-support
- [community-support](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/community-support/SKILL.md): Run a public forum where users help each other, with seeding, moderation, and staff presence that keeps answers accurate. Use when support volume exceeds staffing and questions are broadly shareable.
- [customer-feedback-loop](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/customer-feedback-loop/SKILL.md): Turn support conversations into product change through structured tagging, aggregation, and a route into the roadmap. Use when support hears the same complaints and nothing changes.
- [difficult-customer-conversations](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/difficult-customer-conversations/SKILL.md): Handle angry, distressed, or unreasonable customers without escalating the conflict or capitulating on things you cannot give. Use when a conversation has become emotional rather than transactional.
- [knowledge-base-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/knowledge-base-design/SKILL.md): Build self-serve documentation that answers questions before they become tickets, organised by what people search for. Use when the same questions arrive repeatedly.
- [proactive-support](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/proactive-support/SKILL.md): Reach customers before they contact you, when telemetry or a known issue means they are about to have a problem. Use when failures are detectable before the customer notices or writes in.
- [support-analytics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/support-analytics/SKILL.md): Measure support with metrics that reflect customer outcomes rather than agent activity, and use them to reduce ticket volume. Use when support is measured by throughput and quality is drifting.
- [support-escalation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/support-escalation/SKILL.md): Move a ticket to engineering or management with the context needed to act, and set expectations with the customer while it moves. Use when a ticket cannot be resolved at the current level.
- [support-handoff](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/support-handoff/SKILL.md): Transfer a ticket between agents, shifts, or teams without the customer repeating themselves. Use when work crosses people and context is being lost.
- [support-macros](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/support-macros/SKILL.md): Build reusable reply templates that speed common answers without making replies feel automated. Use when agents retype the same explanations daily.
- [support-response-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/support-response-writing/SKILL.md): Write replies that answer the question, respect the customer's time, and avoid the phrases that make people angrier. Use when writing any customer-facing support message.
- [support-sla-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/support-sla-management/SKILL.md): Set, measure, and honour response and resolution commitments that reflect real capacity rather than aspiration. Use when promising response times to customers or in contracts.
- [support-ticket-triage](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/customer-support/support-ticket-triage/SKILL.md): Sort incoming tickets by urgency and type so the ones that matter are answered first and nothing sits unread. Use when volume exceeds what can be handled in arrival order.
## Skills: data-engineering
- [batch-vs-streaming](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/batch-vs-streaming/SKILL.md): Choose batch or streaming from honest latency requirements and operate the complexity you actually need. Use when designing a data flow or reviewing whether a streaming system earns its cost.
- [change-data-capture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/change-data-capture/SKILL.md): Replicate database changes via log-based CDC with correct snapshot handling, ordering, and schema-change survival. Use when streaming OLTP changes to warehouses, caches, or search without touching app code.
- [data-lineage](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/data-lineage/SKILL.md): Capture table and column-level lineage to answer impact and provenance questions before changes and during incidents. Use when planning schema changes, debugging bad numbers, or building data-platform trust.
- [data-partitioning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/data-partitioning/SKILL.md): Partition datasets by pruning-friendly keys with healthy file sizes and scheduled compaction. Use when laying out lake or warehouse tables, or fixing slow scans and small-file explosions.
- [data-pipeline-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/data-pipeline-design/SKILL.md): Build data pipelines that rerun safely, backfill cleanly, and tolerate late data. Use when designing batch or streaming pipelines or fixing ones that need manual babysitting.
- [data-quality-checks](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/data-quality-checks/SKILL.md): Layer freshness, volume, schema, and distribution checks with quarantine and alert discipline. Use when adding quality gates to pipelines or when consumers keep finding bad data first.
- [data-retention](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/data-retention/SKILL.md): Implement retention tiers, legal holds, and deletion pipelines that actually delete, including GDPR-style erasure. Use when defining how long data lives or building the machinery that enforces it.
- [etl-vs-elt](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/etl-vs-elt/SKILL.md): Place transformations before or after loading based on warehouse economics, governance, and reuse. Use when architecting a data platform or deciding where a transformation should live.
- [incremental-processing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/incremental-processing/SKILL.md): Process only new and changed data with watermarks, merge strategies, and a full-refresh escape hatch. Use when full-table rebuilds get slow or costly and models must go incremental.
- [pipeline-orchestration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/pipeline-orchestration/SKILL.md): Orchestrate data DAGs with data-aware scheduling, bounded retries, and SLAs that page the right owner. Use when structuring workflows in an orchestrator or fixing 3am cron archaeology.
- [schema-evolution](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/schema-evolution/SKILL.md): Evolve data schemas with compatibility rules, producer contracts, and registries so downstream never breaks silently. Use when changing event or table schemas that other teams consume.
- [warehouse-modeling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-engineering/warehouse-modeling/SKILL.md): Model warehouse tables with explicit grain, conformed dimensions, and deliberate SCD handling. Use when designing analytics schemas or fixing double-counted metrics and unjoinable tables.
## Skills: data-privacy
- [consent-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/consent-management/SKILL.md): Ask for, record, and honour consent so processing has a lawful basis and withdrawal actually stops it. Use when adding tracking, marketing, or any optional processing of personal data.
- [cookie-compliance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/cookie-compliance/SKILL.md): Handle cookies and similar storage so non-essential ones only load after consent and the banner reflects reality. Use when adding analytics, embeds, or any client-side storage on a website.
- [cross-border-transfers](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/cross-border-transfers/SKILL.md): Know where personal data physically goes and keep transfers lawful when it crosses a border. Use when choosing a region, adding a vendor, or designing replication and backups.
- [data-anonymization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/data-anonymization/SKILL.md): Remove or blunt identifiers so a dataset can be analysed or shared without re-identifying people, and know when it is only pseudonymous. Use when preparing data for analytics, testing, sharing, or research.
- [data-classification](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/data-classification/SKILL.md): Label data by sensitivity so controls, retention, and access follow the label instead of being argued case by case. Use when designing storage, granting access, or deciding how carefully a dataset must be handled.
- [data-minimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/data-minimization/SKILL.md): Collect and keep only the personal data a feature actually needs, so exposure, cost, and compliance burden all shrink at once. Use when designing a form, an event schema, a log line, or any system that touches personal data.
- [privacy-by-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/privacy-by-design/SKILL.md): Build privacy into a feature from the first design rather than bolting it on before launch. Use when starting any feature that will touch personal data.
- [privacy-impact-assessment](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/privacy-impact-assessment/SKILL.md): Assess a high-risk processing activity before it ships, documenting risks, mitigations, and the decision. Use when processing sensitive data, profiling at scale, or introducing a novel use of personal data.
- [right-to-erasure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/right-to-erasure/SKILL.md): Delete a person's data on request across every store, copy, and backup, and prove it happened. Use when implementing deletion, handling an erasure request, or auditing whether delete really deletes.
- [subject-access-requests](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/subject-access-requests/SKILL.md): Answer a request for a copy of someone's data completely, on time, and without exposing anyone else. Use when building an export path or responding to an access request.
- [vendor-data-processing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-privacy/vendor-data-processing/SKILL.md): Assess and control what third-party services do with personal data you send them, before and after integration. Use when adding a vendor, SDK, or API that will receive user data.
## Skills: data-science
- [cohort-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/cohort-analysis/SKILL.md): Group users by a shared start and track them over time to see retention, behavior, and trends that aggregates hide. Use when a blended metric looks stable or improving but you suspect the underlying behavior is changing.
- [correlation-causation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/correlation-causation/SKILL.md): Tell correlation from causation and avoid the confounding, selection, and reverse-causation traps. Use when data shows a relationship and someone is about to claim one thing causes another.
- [data-cleaning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/data-cleaning/SKILL.md): Clean and prepare messy data (missing values, outliers, types, duplicates) with decisions that preserve signal and avoid leakage. Use when raw data needs to be made analysis-ready without corrupting it.
- [data-storytelling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/data-storytelling/SKILL.md): Turn analysis into a clear narrative that drives a decision, leading with the insight and backing it with the right evidence. Use when presenting findings to stakeholders who need to act, not admire charts.
- [data-visualization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/data-visualization/SKILL.md): Choose and design charts that reveal the truth in data clearly and honestly, matching the chart to the question. Use when visualizing data for exploration or communication, or fixing a misleading or cluttered chart.
- [experiment-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/experiment-analysis/SKILL.md): Analyze A/B test results correctly: effect size with intervals, guardrails, segments, and the peeking and Simpson traps. Use when reading out an experiment and deciding whether the change worked, before you ship it.
- [exploratory-data-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/exploratory-data-analysis/SKILL.md): Explore a new dataset systematically to understand its shape, quality, and signal before modeling. Use when you first get a dataset and need to know what is in it, what is wrong with it, and what is worth pursuing.
- [feature-engineering-tabular](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/feature-engineering-tabular/SKILL.md): Engineer features for tabular models (aggregations, encodings, interactions) that add signal without leaking. Use when building features for a tabular ML or Kaggle problem, where features often matter more than the model.
- [funnel-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/funnel-analysis/SKILL.md): Analyze conversion funnels to find where users drop off and why, and size the opportunity of fixing each step. Use when diagnosing where a multi-step flow loses people, or prioritizing what to fix.
- [gradient-boosting-tuning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/gradient-boosting-tuning/SKILL.md): Tune gradient-boosted trees (XGBoost, LightGBM, CatBoost) effectively: the parameters that matter and the order to tune them. Use when using gradient boosting on tabular data and wanting real gains from tuning.
- [kaggle-competition-workflow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/kaggle-competition-workflow/SKILL.md): Approach a Kaggle (or any ML competition) systematically: trustworthy validation, strong baseline, then disciplined iteration. Use when entering a data competition and want to place well without wasting the timeline.
- [leaderboard-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/leaderboard-strategy/SKILL.md): Trust your cross-validation over the public leaderboard, avoid overfitting it, and select final submissions wisely. Use in the endgame of a Kaggle competition, where rank is won or lost by validation discipline.
- [model-ensembling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/model-ensembling/SKILL.md): Combine diverse models through averaging, blending, and stacking to beat any single model. Use when squeezing maximum accuracy from a competition or high-stakes prediction, after strong single models exist.
- [probability-fundamentals](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/probability-fundamentals/SKILL.md): Reason correctly about probability, base rates, conditional probability, and expected value, avoiding the common intuition traps. Use when interpreting likelihoods, test results, risks, or any uncertain quantity.
- [regression-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/regression-analysis/SKILL.md): Fit and interpret regression models for insight, reading coefficients, fit, and caveats honestly rather than as causal truth. Use when using regression to understand relationships in data, not to build a predictive model.
- [sampling-and-bias](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/sampling-and-bias/SKILL.md): Judge whether a sample represents the population and spot the selection, survivorship, and response biases that invalidate conclusions. Use when drawing conclusions from data that is a sample of something larger, which is almost always.
- [statistical-inference](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/statistical-inference/SKILL.md): Draw honest conclusions from samples using hypothesis tests, confidence intervals, and significance read correctly. Use when deciding whether an effect is real, comparing groups, or reporting uncertainty.
- [time-series-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/data-science/time-series-analysis/SKILL.md): Analyze and forecast time-ordered data respecting trend, seasonality, autocorrelation, and the arrow of time. Use when working with data indexed by time: metrics, sales, sensor readings, or any forecast.
## Skills: databases
- [backup-restore](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/backup-restore/SKILL.md): Design backups around tested restores, point-in-time recovery, and backup security. Use when setting up database backups or verifying that existing backups would actually work in a disaster.
- [database-migrations](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/database-migrations/SKILL.md): Change schemas safely with expand-contract, online DDL, batched backfills, and rollback awareness. Use when altering a production schema or when a migration risks locking or downtime.
- [database-normalization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/database-normalization/SKILL.md): Apply normal forms pragmatically and denormalize deliberately, weighing update anomalies against read performance. Use when designing a relational schema or deciding whether to denormalize.
- [indexing-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/indexing-strategy/SKILL.md): Design indexes from query patterns with correct column order, covering indexes, and write-cost awareness. Use when queries are slow or a table has too many or too few indexes.
- [nosql-modeling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/nosql-modeling/SKILL.md): Model NoSQL data from access patterns first, with single-table and denormalization discipline. Use when designing for a document or key-value store, or when a relational mindset is fighting a NoSQL database.
- [orm-tradeoffs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/orm-tradeoffs/SKILL.md): Use ORMs for their productivity while avoiding N+1 queries and knowing when to drop to raw SQL. Use when working with an ORM or debugging the performance problems ORMs quietly cause.
- [query-plan-reading](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/query-plan-reading/SKILL.md): Read EXPLAIN ANALYZE output to find the real cause of a slow query and fix the right thing. Use when a query is slow and you need to know why before changing indexes or SQL.
- [schema-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/schema-design/SKILL.md): Design database schemas that stay correct under growth and change. Use when creating tables, modeling relationships, or planning schema migrations.
- [sharding-partitioning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/sharding-partitioning/SKILL.md): Scale databases by partitioning and sharding with a good key, handling resharding and cross-shard queries, and knowing when to avoid it. Use when one database can no longer hold or serve the load.
- [sql-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/sql-optimization/SKILL.md): Diagnose and fix slow SQL with the query plan as evidence, not folklore. Use when a query is slow, a table scan appears, or database load climbs.
- [time-series-data](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/time-series-data/SKILL.md): Store time-series data with retention downsampling, compression, out-of-order handling, and the right store choice. Use when handling metrics, events, or sensor streams that grow relentlessly by time.
- [transactions-isolation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/databases/transactions-isolation/SKILL.md): Choose isolation levels by the anomalies they prevent, understand locking versus MVCC, and retry on serialization failures. Use when transactional correctness matters or concurrency bugs appear under load.
## Skills: debugging
- [alerting-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/alerting-design/SKILL.md): Design alerts that fire on the symptoms users feel, using error-budget burn rate, a page-worthiness test, and a runbook link on every rule. Use when writing or pruning alerts and you want the pager to mean something instead of crying wolf.
- [binary-search-debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/binary-search-debugging/SKILL.md): Halve the search space repeatedly across code, data, time, and configuration until a single change isolates the failure. Use when the fault could live anywhere across a large surface and reading it all in order is too slow.
- [browser-devtools](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/browser-devtools/SKILL.md): Debug a slow or broken web page with the browser's built-in tools: the network waterfall, the performance panel, and source maps back to original code. Use when a page loads slowly, janks while running, or throws in minified bundle code you cannot read.
- [core-dumps](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/core-dumps/SKILL.md): Extract the cause of a crash from a core dump using symbols, backtraces, and post-mortem inspection. Use when a native process died with a signal and left a core file, or when you have a crash dump but no live process to attach to.
- [dashboard-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/dashboard-design/SKILL.md): Build dashboards where each panel answers exactly one question, laid out by the RED method for services and the USE method for resources. Use when a board has grown into a wall of graphs nobody can read while an incident burns.
- [deadlock-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/deadlock-analysis/SKILL.md): Find why threads are stuck forever by dumping their state and building the wait-for graph that reveals the lock cycle. Use when a program hangs with no progress and no crash, or throughput drops to zero while CPU sits idle.
- [debugger-fluency](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/debugger-fluency/SKILL.md): Drive a real debugger with breakpoints, watch expressions, and conditional stops to read live program state at the moment of failure. Use when a bug needs you to see the call stack and variables as it breaks, not reconstruct them afterward.
- [debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/debugging/SKILL.md): Find the root cause of a bug with a hypothesis-driven loop instead of guess-and-patch. Use when something fails, crashes, or behaves wrongly and the cause is not yet known.
- [distributed-tracing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/distributed-tracing/SKILL.md): Follow one request across service boundaries using spans, propagated context, and critical-path reading to locate where latency and errors originate. Use when a request is slow or failing and the cause lives between services, not inside any single one.
- [error-tracking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/error-tracking/SKILL.md): Wire an error tracker to releases, tune grouping rules, and route each issue to an owner so exceptions become triaged work. Use when exceptions vanish into log noise and nobody knows which are new, which are spiking, or whose they are.
- [flaky-test-diagnosis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/flaky-test-diagnosis/SKILL.md): Turn a test that fails at random into one that fails on demand by controlling the seed, order, and clock. Use when a test passes on re-run, fails only in CI, or blocks a merge for reasons no one can reproduce.
- [git-bisect](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/git-bisect/SKILL.md): Find the exact commit that introduced a regression by driving git bisect with an automated pass/fail script. Use when a behavior worked in an older build and you need the first bad commit out of hundreds, not a guess.
- [heisenbugs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/heisenbugs/SKILL.md): Catch timing-dependent bugs that vanish under observation by amplifying the race and moving logging off the critical path. Use when a fault appears intermittently and disappears the moment you add a print or attach a debugger.
- [log-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/log-analysis/SKILL.md): Mine logs for the cause of a failure by pivoting on correlation ids, clamping the time window, and querying structured fields instead of scrolling. Use when production broke and the logs are the only record of what the system actually did.
- [log-levels](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/log-levels/SKILL.md): Assign log levels deliberately so error wakes a human, warn flags a trend, and info and debug explain later without burying the signal. Use when logs are either silent during real failures or so noisy that nobody trusts them.
- [memory-leaks](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/memory-leaks/SKILL.md): Find the object that never gets freed by comparing heap snapshots and following retention paths. Use when a process grows in memory over time, gets OOM-killed, or slows under a garbage collector that keeps working harder.
- [metrics-instrumentation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/metrics-instrumentation/SKILL.md): Instrument code with counters, gauges, and histograms picked to answer a specific operational question. Use when you need to watch a system's behavior over time and want the right instrument instead of a wall of unreadable numbers.
- [network-debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/network-debugging/SKILL.md): Diagnose failing or slow network calls by inspecting the actual bytes on the wire with curl, tcpdump, and TLS handshake analysis. Use when a request fails, hangs, or returns the wrong thing and you cannot tell whether the client, the network, or the server is at fault.
- [observability](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/observability/SKILL.md): Instrument software so production questions get answered from signals, not guesses. Use when adding logging, metrics, tracing, or alerts, or when a system is hard to debug in production.
- [off-by-one-errors](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/off-by-one-errors/SKILL.md): Catch fencepost bugs by writing down the boundary convention and testing the endpoints instead of the middle. Use when a loop, slice, index, or range is off by a single element, drops the last item, or reads one past the end.
- [postmortem-debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/postmortem-debugging/SKILL.md): Reconstruct what happened from the artifacts a dead incident left behind: logs, metrics, dumps, and a timeline, when there is no live system left to poke. Use when the outage is over, the process is gone, and all you have is what was written down while it burned.
- [print-debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/print-debugging/SKILL.md): Place labeled, greppable print statements at decision points to trace the real execution, then remove them cleanly. Use when a debugger is unavailable or awkward and you need to watch values flow through the actual run.
- [production-debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/production-debugging/SKILL.md): Debug a live system without making the incident worse by staying read-only first, gating changes behind flags, and testing on mirrored traffic. Use when a bug only manifests in production and you must investigate against real users and real data.
- [profiling-cpu](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/profiling-cpu/SKILL.md): Find the code that actually burns CPU time using a sampling profiler and a flame graph instead of guesswork. Use when a program is slower than it should be and you need to locate the hot path before touching any code.
- [profiling-memory](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/profiling-memory/SKILL.md): Attribute memory growth and allocation churn to the exact call sites that produce it using an allocation profiler. Use when a process grows without bound, spends too much time in garbage collection, or allocates far more than its working set explains.
- [race-conditions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/race-conditions/SKILL.md): Diagnose data races by reasoning about happens-before order, running sanitizers, and stressing the timing until the bug shows. Use when a bug appears only under load, only sometimes, or vanishes when you add a print statement.
- [reproduction-first](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/reproduction-first/SKILL.md): Build a reliable, minimal reproduction before you write a fix so you can prove the bug is actually gone. Use when a report is vague, intermittent, or "works on my machine" and you need solid ground under the debugging.
- [rubber-duck-protocol](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/rubber-duck-protocol/SKILL.md): Explain the failing code line by line in writing until the sentence you cannot finish exposes the false assumption. Use when you are stuck, re-reading the same code, sure it should work, and it does not.
- [scientific-debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/scientific-debugging/SKILL.md): Debug by turning a belief about the code into a falsifiable hypothesis, predicting an observable, and running the one probe that can refute it. Use when a bug resists guesswork and shotgun edits are making the code murkier instead of the cause clearer.
- [stack-trace-reading](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/stack-trace-reading/SKILL.md): Read a stack trace to find the cause frame instead of stopping at the symptom on top. Use when an exception, panic, or error dump lands and you need to locate the line that is actually wrong.
- [structured-logging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/structured-logging/SKILL.md): Emit machine-readable key-value events instead of prose sentences, with a stable schema and controlled field cardinality. Use when logs need to be queried and aggregated, not just read one line at a time by a person.
- [time-travel-debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/debugging/time-travel-debugging/SKILL.md): Record an execution once and replay it deterministically so you can step backward to the moment a value went wrong. Use when a bug is hard to reproduce or the failure surfaces long after its cause, and rerunning changes the outcome.
## Skills: deep-learning
- [attention-mechanism](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/attention-mechanism/SKILL.md): Understand what attention computes and why its cost grows quadratically with sequence length, to reason about context limits and efficiency work. Use when working with transformer models or evaluating long-context claims.
- [backpropagation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/backpropagation/SKILL.md): Understand how gradients flow backward through a network so vanishing gradients, dead units, and exploding losses become diagnosable. Use when training does not converge or a network learns nothing.
- [batch-size-effects](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/batch-size-effects/SKILL.md): Choose batch size understanding its effect on gradient noise, memory, throughput, and generalisation, and adjust the learning rate with it. Use when scaling training or running out of memory.
- [learning-rate-schedules](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/learning-rate-schedules/SKILL.md): Set and vary the learning rate over training, since it is the hyperparameter that most determines whether a run converges. Use when loss diverges, plateaus early, or oscillates.
- [loss-function-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/loss-function-selection/SKILL.md): Choose a loss that matches the task and the metric you care about, and understand what each penalises. Use when a model optimises well and performs badly on the thing that matters.
- [optimizer-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/optimizer-selection/SKILL.md): Choose an optimiser and its hyperparameters based on the problem rather than habit, and know what each actually does. Use when training is unstable, slow to converge, or generalising poorly.
- [overfitting-diagnosis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/overfitting-diagnosis/SKILL.md): Distinguish overfitting from underfitting, data leakage, and distribution shift, since all four present as poor validation performance. Use when validation performance is worse than expected.
- [regularization-techniques](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/regularization-techniques/SKILL.md): Reduce overfitting with weight decay, dropout, augmentation, and early stopping, choosing by why the model is overfitting. Use when validation performance diverges from training performance.
- [scaling-laws](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/scaling-laws/SKILL.md): Reason about how model performance improves with parameters, data, and compute, to allocate a training budget sensibly. Use when planning a training run or evaluating claims about model size.
- [tokenization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/tokenization/SKILL.md): Understand how text becomes tokens, and why token boundaries explain model behaviour on numbers, code, and non-English text. Use when a model behaves strangely on specific strings or costs more than expected.
- [training-loop-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/training-loop-design/SKILL.md): Structure a training loop with correct ordering, evaluation, checkpointing, and logging so runs are debuggable and resumable. Use when writing or reviewing training code.
- [weight-initialization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deep-learning/weight-initialization/SKILL.md): Initialise parameters so signal and gradients propagate at usable scale from the first step. Use when a deep network fails to train from the start or diverges immediately.
## Skills: deliverables
- [dashboard-building](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/dashboard-building/SKILL.md): Build dashboards that answer specific questions at a glance, rather than displaying every available metric. Use when a team needs shared visibility into an ongoing situation.
- [documentation-site](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/documentation-site/SKILL.md): Structure a documentation site so readers find answers by task, with working examples and a maintenance path. Use when documenting a product or library for external users.
- [form-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/form-design/SKILL.md): Design forms people complete, with the fewest fields, clear labels, and error handling that helps rather than punishes. Use when collecting any information from users.
- [newsletter-production](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/newsletter-production/SKILL.md): Produce a recurring newsletter with a sustainable format, a clear reason to open, and rendering that survives email clients. Use when publishing regularly to a subscribed audience.
- [pdf-generation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/pdf-generation/SKILL.md): Produce PDFs programmatically with correct fonts, page breaks, and accessibility, from templates that survive content changes. Use when generating invoices, reports, certificates, or statements.
- [print-ready-output](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/print-ready-output/SKILL.md): Prepare documents for physical printing with correct colour, bleed, resolution, and fonts, so what prints matches what you designed. Use when producing anything that will be professionally printed.
- [proposal-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/proposal-writing/SKILL.md): Write a proposal that states the client's problem, your approach, and the commercial terms clearly enough to be accepted or declined quickly. Use when bidding for work or pitching a project.
- [report-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/report-writing/SKILL.md): Write a report that leads with findings, supports them with evidence, and states its own limitations. Use when presenting analysis, results, or an investigation in writing.
- [slide-deck-creation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/slide-deck-creation/SKILL.md): Build a deck that supports a spoken argument, with one idea per slide and visuals that carry meaning. Use when presenting to an audience rather than sending a document.
- [spreadsheet-modeling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/spreadsheet-modeling/SKILL.md): Build spreadsheet models that are auditable and hard to break, separating inputs, calculations, and outputs. Use when modelling finances, forecasts, or scenarios.
- [technical-diagrams](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/technical-diagrams/SKILL.md): Draw system, sequence, and flow diagrams that clarify rather than decorate, at a consistent level of abstraction. Use when explaining a system to people who did not build it.
- [website-building](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/deliverables/website-building/SKILL.md): Build and ship a small site that loads fast, reads well, and can be updated, choosing the simplest stack that fits. Use when creating a marketing site, portfolio, documentation site, or landing page.
## Skills: devops
- [artifact-versioning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/artifact-versioning/SKILL.md): Build immutable, provenance-tracked artifacts promoted unchanged through environments. Use when designing a build pipeline or fixing "works in staging, breaks in prod" from rebuilt binaries.
- [blue-green-deployments](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/blue-green-deployments/SKILL.md): Deploy with two swappable environments for instant cutover and rollback, handling database compatibility. Use when zero-downtime releases matter or designing a low-risk deploy mechanism.
- [capacity-planning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/capacity-planning/SKILL.md): Forecast load, size headroom, discover scaling limits before they bite, and track cost curves. Use when planning capacity for growth or a known traffic event, or after a saturation incident.
- [ci-cd](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/ci-cd/SKILL.md): Build CI/CD pipelines that are fast, trustworthy, and safe to deploy from. Use when creating or fixing continuous integration, delivery workflows, or release automation.
- [config-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/config-management/SKILL.md): Separate config from code and secrets, keep environments at parity, and change config safely. Use when wiring application configuration for deployment or fixing environment-specific bugs and config drift.
- [containerization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/containerization/SKILL.md): Write container images and compose setups that are small, reproducible, and safe to run. Use when writing Dockerfiles, docker-compose files, or debugging container behavior.
- [dependency-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/dependency-management/SKILL.md): Choose, add, upgrade, and remove dependencies with the long-term cost in view. Use when adding a library, resolving version conflicts, or auditing a dependency tree.
- [deployment-pipelines](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/deployment-pipelines/SKILL.md): Design deploy pipelines with staged gates, environment promotion, and speed budgets that keep releases safe and frequent. Use when building a CD pipeline or fixing slow, flaky, or unsafe deploys.
- [docker-image-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/docker-image-optimization/SKILL.md): Build small, fast, secure container images with layer caching, multi-stage builds, and a minimal base policy. Use when images are bloated, slow to build, or failing security scans.
- [gitops-workflow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/gitops-workflow/SKILL.md): Manage deployments declaratively from git as the source of truth, with reconciliation, secrets handling, and drift alerts. Use when adopting GitOps or fixing config drift and untracked cluster changes.
- [incident-postmortem](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/incident-postmortem/SKILL.md): Write a blameless postmortem that finds systemic causes and produces actions that actually prevent recurrence. Use after an outage, data incident, or serious bug reaches users.
- [infrastructure-monitoring](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/infrastructure-monitoring/SKILL.md): Monitor systems with the golden signals and USE method, alerts that page only on user impact, and runbook-linked responses. Use when instrumenting infrastructure or fixing alert fatigue.
- [rollback-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/rollback-strategy/SKILL.md): Decide rollback versus fix-forward, handle migrations safely, and rehearse rollbacks so they work under pressure. Use when planning deploy safety or during an incident deciding how to recover.
- [runbook-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/devops/runbook-writing/SKILL.md): Write runbooks with executable steps, decision points, and per-step verification that a stressed responder can follow. Use when documenting operational procedures or reducing 3am guesswork.
## Skills: distributed-systems
- [backpressure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/backpressure/SKILL.md): Bound every queue and propagate overload upstream so systems degrade by shedding instead of collapsing. Use when designing high-throughput paths or diagnosing latency spirals under load.
- [clock-skew](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/clock-skew/SKILL.md): Stop trusting wall clocks for ordering and expiry across machines; use logical clocks and single-writer timestamps. Use when timestamps decide ordering, uniqueness, or expiry in a distributed system.
- [consensus-basics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/consensus-basics/SKILL.md): Understand what Raft and Paxos actually provide, quorum arithmetic, and when you need consensus at all. Use when deploying replicated coordination systems or deciding whether a problem truly requires consensus.
- [consistency-models](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/consistency-models/SKILL.md): Choose the weakest consistency model each use case tolerates, from linearizable to eventual. Use when designing replicated data paths or explaining anomalies users report as bugs.
- [cqrs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/cqrs/SKILL.md): Split read and write models when their shapes genuinely diverge, and manage the sync lag honestly. Use when one data model cannot serve both commands and queries well, or when reviewing an over-engineered CQRS setup.
- [delivery-guarantees](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/delivery-guarantees/SKILL.md): Reason honestly about at-most-once, at-least-once, and effectively-once semantics end to end. Use when specifying messaging behavior or auditing where a pipeline can lose or duplicate data.
- [distributed-locks](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/distributed-locks/SKILL.md): Use leases with fencing tokens for mutual exclusion across machines, or restructure to need no lock at all. Use when serializing distributed work or reviewing lock code that must not double-execute.
- [event-sourcing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/event-sourcing/SKILL.md): Persist state as an append-only event log with projections and snapshots, and know when the pattern is overkill. Use when audit history is a first-class requirement or evaluating event sourcing against CRUD.
- [idempotent-consumers](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/idempotent-consumers/SKILL.md): Make message consumers safe under at-least-once delivery with natural idempotency or a transactional dedup store. Use when building queue/stream consumers or debugging duplicate side effects.
- [leader-election](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/leader-election/SKILL.md): Run one active node with lease-based election, split-brain prevention, and clean handoff. Use when exactly one instance must do a job (scheduler, migrator, singleton consumer) across a fleet.
- [partition-tolerance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/partition-tolerance/SKILL.md): Decide per operation what happens during a network partition, and design degraded modes that fail safe. Use when planning multi-node or multi-region behavior under network failure.
- [saga-pattern](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/distributed-systems/saga-pattern/SKILL.md): Coordinate multi-service transactions as a sequence of local steps with compensations, timeouts, and an observable state machine. Use when a business flow spans services and two-phase commit is not on the table.
## Skills: documentation
- [api-reference-docs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/api-reference-docs/SKILL.md): Produce API reference docs that blend generation with curation, an example per endpoint, and documented errors. Use when documenting an API or SDK for external or internal consumers.
- [changelog-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/changelog-writing/SKILL.md): Write changelogs for humans, grouped by change type, with breaking changes called out and versions dated. Use when maintaining a changelog or replacing raw commit dumps with useful release notes.
- [code-documentation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/code-documentation/SKILL.md): Write code comments and API docs that carry what the code cannot say, and nothing it already does. Use when documenting functions, modules, or tricky passages.
- [docs-as-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/docs-as-code/SKILL.md): Treat documentation like code: in the repo, in pull requests, CI-checked, with preview builds. Use when docs drift from reality or the docs workflow is separate from the code workflow.
- [docs-information-architecture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/docs-information-architecture/SKILL.md): Organize documentation with the Diataxis four-quadrant model, navigable structure, and searchability. Use when structuring a docs site or when readers cannot find what they need.
- [docs-maintenance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/docs-maintenance/SKILL.md): Keep documentation from rotting through staleness detection, ownership, doc tests, and deliberate deprecation. Use when docs have drifted from reality or no process keeps them current.
- [onboarding-docs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/onboarding-docs/SKILL.md): Write onboarding docs that get a new contributor to a verified working setup and a first contribution fast. Use when new joiners struggle to get started or setup instructions keep breaking.
- [readme-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/readme-writing/SKILL.md): Write READMEs that deliver value on the first screen, quickstart before reference, and stay maintainable. Use when creating or fixing a project's front-door documentation.
- [technical-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/technical-writing/SKILL.md): Write documentation, READMEs, and guides that respect the reader's time and answer their actual question. Use when drafting or editing any technical document.
- [tutorial-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/documentation/tutorial-writing/SKILL.md): Write tutorials that take a learner from zero to a working result through tested steps with checkpoints and recovery. Use when creating learning-oriented documentation or onboarding guides.
## Skills: email
- [clear-emails](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/email/clear-emails/SKILL.md): Write emails that get read and acted on: one clear purpose, the ask up front, and only what the reader needs. Use when writing any email that must be understood and answered without back-and-forth.
- [difficult-emails](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/email/difficult-emails/SKILL.md): Write the hard emails (bad news, saying no, complaints, corrections) so they are clear, kind, and preserve the relationship. Use when an email must deliver something unwelcome without making it worse.
- [email-etiquette](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/email/email-etiquette/SKILL.md): Follow email conventions that keep you professional and considerate: CC/BCC, reply-all, response times, and threading. Use when unsure of the norms, or to avoid the mistakes that annoy colleagues and burn goodwill.
- [email-follow-ups](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/email/email-follow-ups/SKILL.md): Follow up on unanswered emails effectively: the right timing, adding value, and knowing when to stop. Use when an email went unanswered and you need a reply without nagging or damaging the relationship.
- [email-structure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/email/email-structure/SKILL.md): Structure an email so a skimming reader gets the point, the context, and the ask in the right order. Use when an email has more than a line or two and the layout decides whether it is understood.
- [email-subject-lines](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/email/email-subject-lines/SKILL.md): Write subject lines that get emails opened and found later: specific, honest, and action-signaling. Use when the subject line decides whether your email is opened, prioritized, or buried.
- [email-tone](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/email/email-tone/SKILL.md): Get the tone of an email right: warm, professional, and matched to the reader and situation, without the coldness email invites. Use when an email's wording could land wrong, or when the relationship matters as much as the message.
- [inbox-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/email/inbox-management/SKILL.md): Manage an email inbox so it is a task list you control, not a source of stress: triage, process, and protect focus. Use when email volume is overwhelming or the inbox has become an anxiety pile.
## Skills: embedded-iot
- [embedded-debugging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/embedded-iot/embedded-debugging/SKILL.md): Debug firmware with JTAG/SWD workflows, console-free logging, and hard-fault analysis that names the faulting line. Use when a device crashes, hangs, or misbehaves only in the field.
- [embedded-memory-constraints](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/embedded-iot/embedded-memory-constraints/SKILL.md): Fit firmware into kilobytes with static allocation, measured stack sizing, and linker-map budgeting. Use when developing on microcontrollers or debugging overflows and fragmentation on-device.
- [firmware-ota-updates](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/embedded-iot/firmware-ota-updates/SKILL.md): Ship over-the-air firmware with A/B slots, signed images, power-loss resilience, and staged fleet rollout. Use when building device update systems or reviewing one before it bricks a fleet.
- [interrupt-safe-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/embedded-iot/interrupt-safe-code/SKILL.md): Write ISRs that stay minimal, share data through volatile-correct handoffs, and defer real work safely. Use when writing interrupt handlers or debugging corruption that only happens sometimes.
- [iot-messaging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/embedded-iot/iot-messaging/SKILL.md): Connect device fleets with MQTT topic design, QoS chosen per message class, offline buffering, and safe fleet commands. Use when designing device-to-cloud messaging or debugging lost telemetry and stuck commands.
- [low-power-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/embedded-iot/low-power-design/SKILL.md): Reach battery-life targets through sleep-state budgeting, duty cycling, and measured (not estimated) current draw. Use when designing battery-powered devices or hunting a power regression.
- [rtos-task-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/embedded-iot/rtos-task-design/SKILL.md): Decompose firmware into RTOS tasks with deadline-derived priorities, queue-based communication, and priority-inversion defenses. Use when structuring FreeRTOS/Zephyr-class applications or debugging missed deadlines.
- [sensor-data-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/embedded-iot/sensor-data-handling/SKILL.md): Turn raw sensor readings into trustworthy data with correct sampling, filtering, calibration, and timestamped batching. Use when building sensor pipelines or debugging noisy, aliased, or drifting measurements.
## Skills: frontend
- [design-systems](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/design-systems/SKILL.md): Build and maintain a design system that keeps a product visually consistent and fast to build. Use when creating design tokens, component libraries, or UI guidelines.
- [error-boundaries-ui](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/error-boundaries-ui/SKILL.md): Isolate render failures behind boundaries with useful fallbacks, retry, and reporting so one broken component does not blank the app. Use when adding error boundaries, designing failure UI, or a crash takes down a whole page.
- [form-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/form-handling/SKILL.md): Build forms with validation timing, error display, and submission states that respect users and screen readers. Use when creating or reviewing any form, or fixing premature-error or lost-input complaints.
- [frontend-routing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/frontend-routing/SKILL.md): Structure client routes so the URL is the source of truth, data loads per route, and back/scroll behave. Use when adding routes, wiring route data loading, or fixing lost-filter or scroll-jump bugs.
- [frontend-state](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/frontend-state/SKILL.md): Decide where frontend state lives and how it flows, so UIs stay predictable as they grow. Use when structuring components, adding state, or untangling prop-drilling and sync bugs.
- [list-virtualization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/list-virtualization/SKILL.md): Virtualize long lists so only visible rows mount, with correct handling of dynamic heights and scroll anchoring. Use when a long list or table janks, or before building any list that can grow unbounded.
- [optimistic-ui](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/optimistic-ui/SKILL.md): Apply optimistic updates with correct rollback, conflict handling, and pending cues so mutations feel instant without lying. Use when a mutation feels slow, or when adding or debugging optimistic updates and their rollbacks.
- [react-component-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/react-component-design/SKILL.md): Design React component props and boundaries so components compose cleanly and stay reusable. Use when creating a component, reviewing a bloated props list, or deciding controlled versus uncontrolled.
- [react-hooks-discipline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/react-hooks-discipline/SKILL.md): Write React hooks with correct dependencies and minimal effects so renders stay predictable. Use when adding useEffect, debugging stale closures or render loops, or extracting a custom hook.
- [ui-state-machines](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/frontend/ui-state-machines/SKILL.md): Model UI as explicit finite states so impossible combinations cannot render. Use when a component juggles interacting booleans, shows contradictory states, or a flow has grown too many flags to reason about.
## Skills: game-development
- [entity-component-system](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/game-development/entity-component-system/SKILL.md): Model game objects as entities with data components processed by systems, and know when ECS complexity pays. Use when structuring game architecture or escaping deep inheritance hierarchies.
- [game-asset-pipeline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/game-development/game-asset-pipeline/SKILL.md): Automate asset import, atlasing, compression, and hot reload so content flows from tools to game without hand steps. Use when building content pipelines or fixing bloated builds and stale assets.
- [game-input-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/game-development/game-input-handling/SKILL.md): Build input systems with action mapping, buffering, dead zones, and rebinding that feel responsive and fair. Use when wiring game controls or fixing input that feels laggy or eats presses.
- [game-loop-architecture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/game-development/game-loop-architecture/SKILL.md): Structure game loops with fixed-timestep simulation, interpolated rendering, and spiral-of-death protection. Use when building a game loop or fixing physics that behaves differently across frame rates.
- [game-performance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/game-development/game-performance/SKILL.md): Hold frame budgets through per-frame profiling, object pooling, draw-call batching, and allocation discipline. Use when a game stutters, drops frames, or needs optimization triage.
- [game-save-systems](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/game-development/game-save-systems/SKILL.md): Build save systems with versioned formats, corruption resistance, and autosave that never loses real progress. Use when designing game persistence or debugging broken saves after updates.
- [multiplayer-netcode](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/game-development/multiplayer-netcode/SKILL.md): Build multiplayer with an authoritative server, client prediction, reconciliation, and lag compensation. Use when adding networking to a game or fixing rubber-banding and desync.
- [procedural-generation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/game-development/procedural-generation/SKILL.md): Generate game content with seeded determinism, layered noise, constraint solving, and validation that guarantees playability. Use when building procedural levels, worlds, or loot, or debugging generation that breaks.
## Skills: git-collaboration
- [branch-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/branch-strategy/SKILL.md): Choose a branching model, default to trunk-based with short-lived branches, and set protection rules. Use when establishing team git workflow or fixing long-lived-branch merge pain.
- [code-owners](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/code-owners/SKILL.md): Design CODEOWNERS to route reviews and balance load without turning ownership into a gatekeeping bottleneck. Use when setting up review routing or fixing slow reviews and unclear responsibility.
- [commit-messages](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/commit-messages/SKILL.md): Write commit messages that explain change and intent so history stays useful. Use when committing work or asked to draft a commit message for a diff.
- [git-history-hygiene](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/git-history-hygiene/SKILL.md): Keep git history atomic, bisectable, and readable with curated commits and disciplined force-push. Use when commits are messy, history is hard to navigate, or bisect and blame mislead.
- [git-hooks-automation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/git-hooks-automation/SKILL.md): Automate checks with git hooks that stay fast, with server-side enforcement and documented escape hatches. Use when setting up pre-commit checks or fixing hooks that developers routinely bypass.
- [git-workflow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/git-workflow/SKILL.md): Use git safely and legibly: branches, history, merges, conflicts, and recovery. Use when managing branches, cleaning history, resolving conflicts, or undoing mistakes.
- [merge-vs-rebase](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/merge-vs-rebase/SKILL.md): Choose merge or rebase by the history you want, use interactive rebase safely, and set a team policy. Use when deciding integration mechanics or resolving debates about git history style.
- [monorepo-vs-polyrepo](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/monorepo-vs-polyrepo/SKILL.md): Decide between one repository and many by tooling readiness, coupling, and team autonomy, and plan the migration. Use when structuring repositories for multiple projects or reconsidering a painful split.
- [pull-request-size](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/pull-request-size/SKILL.md): Keep pull requests small through vertical slicing and stacking, because review quality and latency both collapse with size. Use when PRs are too big to review well or sit for days.
- [release-tagging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/git-collaboration/release-tagging/SKILL.md): Tag releases with semantic versions and signed tags, generate changelogs, and trigger builds from tags. Use when setting up a release process or fixing ambiguous, unsigned, or manual releases.
## Skills: github-platform
- [actions-security](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/actions-security/SKILL.md): Prevent workflow automation from becoming an attack path, through pinned actions, scoped tokens, and careful handling of untrusted input. Use when workflows handle secrets or run on pull requests from forks.
- [branch-protection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/branch-protection/SKILL.md): Configure rules that stop unreviewed or broken code reaching the default branch, without making routine work impossible. Use when setting up a shared repository or after an incident traced to a direct push.
- [dependency-scanning-setup](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/dependency-scanning-setup/SKILL.md): Configure automated dependency and vulnerability scanning at a cadence people will actually act on. Use when dependencies drift or vulnerabilities go unnoticed.
- [github-actions-workflows](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/github-actions-workflows/SKILL.md): Write CI workflows that are fast, readable, and cheap, with the right triggers, caching, and matrix strategy. Use when setting up or fixing automation on a repository.
- [github-api-automation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/github-api-automation/SKILL.md): Script repository operations reliably, respecting rate limits, pagination, and permissions. Use when managing repositories at scale or building tooling around the platform.
- [issue-and-project-tracking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/issue-and-project-tracking/SKILL.md): Structure issues, labels, and boards so the tracker reflects reality and answers what is being worked on. Use when the backlog has grown beyond what anyone reads.
- [pr-automation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/pr-automation/SKILL.md): Automate the mechanical parts of pull requests, such as labelling, assignment, checks, and merging, so review effort goes to the code. Use when review process consumes attention on bookkeeping.
- [release-automation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/release-automation/SKILL.md): Automate tagging, building, and publishing releases so shipping is repeatable and the artefacts match the tag. Use when releases are manual, inconsistent, or occasionally wrong.
- [repository-hygiene](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/repository-hygiene/SKILL.md): Keep a repository free of stale branches, dead files, oversized objects, and abandoned configuration. Use when a repository has grown cluttered or slow to clone.
- [repository-permissions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/repository-permissions/SKILL.md): Grant repository and organisation access through teams and least privilege, and review it before it drifts. Use when managing access for a growing organisation or auditing who can do what.
- [repository-structure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/repository-structure/SKILL.md): Organise a repository so a newcomer finds what they need and automation has predictable paths. Use when starting a repository or when nobody can find anything in an existing one.
- [secret-scanning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/github-platform/secret-scanning/SKILL.md): Detect committed credentials, respond correctly when one is found, and prevent the next one. Use when setting up a repository or after a credential appears in history.
## Skills: gpu-ai-infrastructure
- [ai-datacenter-networking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/ai-datacenter-networking/SKILL.md): Lay out the network for distributed training so collectives run on the fastest link that spans them, using NVLink, InfiniBand, and topology-aware placement. Use when a training job spans multiple GPUs or nodes and interconnect, not compute, is capping throughput.
- [checkpointing-large-training](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/checkpointing-large-training/SKILL.md): Checkpoint multi-node training runs so a save costs seconds instead of minutes and a resume reproduces the run exactly. Use when a job is large enough that a crash without a recent, verified checkpoint means losing hours of GPU time.
- [cuda-kernel-basics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/cuda-kernel-basics/SKILL.md): Write first CUDA kernels that map work onto the grid, coalesce global memory, and keep enough warps resident to hide latency. Use when hand-writing or reviewing a CUDA kernel and it runs far below the bandwidth or FLOPs the card should reach.
- [distributed-training-scaling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/distributed-training-scaling/SKILL.md): Scale training from one GPU to many by moving through data parallel and sharded FSDP modes, overlapping communication with compute, and reading the efficiency curve to find the ceiling. Use when adding GPUs stops making training proportionally faster and you need to locate where the scaling leaks.
- [fault-tolerant-training](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/fault-tolerant-training/SKILL.md): Keep a long training job alive across GPU failures, node evictions, and stragglers so one bad host costs minutes, not the whole run. Use when a run spans enough GPUs and hours that hardware failure during the job is expected, not hypothetical.
- [gpu-cluster-scheduling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/gpu-cluster-scheduling/SKILL.md): Schedule GPU jobs on a shared cluster so distributed jobs get all their GPUs at once, fragmentation stays low, and preemption is predictable. Use when several teams share a GPU pool and jobs sit pending while GPUs sit idle.
- [gpu-cost-planning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/gpu-cost-planning/SKILL.md): Plan GPU spend by comparing owned hardware, reserved cloud, and on-demand against real utilization and lead time, so you commit at the right break-even. Use when deciding whether to buy GPUs, reserve cloud capacity, or burst on-demand for a workload.
- [gpu-memory-hierarchy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/gpu-memory-hierarchy/SKILL.md): Place data across the GPU memory tiers so a kernel is limited by math rather than by repeated trips to HBM. Use when a kernel is memory-bound, when deciding what to stage in shared memory or L2, or when register spills are stalling a hot loop.
- [gpu-sharing-mig](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/gpu-sharing-mig/SKILL.md): Share one physical GPU across several small workloads using MIG, MPS, or time slicing, and pick the mode whose isolation matches the risk. Use when GPUs sit at low utilization because each job needs far less than a whole A100 or H100.
- [gpu-utilization-monitoring](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/gpu-utilization-monitoring/SKILL.md): Monitor a GPU fleet so you can tell a genuinely busy GPU from one reporting 100 percent utilization while computing almost nothing, and find the wasted spend. Use when GPUs look busy on the dashboard but throughput or cost per token says otherwise.
- [inference-serving-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/inference-serving-optimization/SKILL.md): Tune LLM serving to hold latency SLOs while raising GPU throughput, working the batch scheduler, KV cache, and paged attention together. Use when a serving replica misses its latency target or leaves memory and utilization on the table.
- [kernel-profiling-nsight](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/kernel-profiling-nsight/SKILL.md): Profile GPU work with Nsight Systems and Nsight Compute to read the timeline, name the bottleneck class, and pull the metric that dictates the fix. Use when a GPU program is slower than expected and you need evidence before touching a kernel.
- [mixed-precision-deployment](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/mixed-precision-deployment/SKILL.md): Ship FP16, BF16, or FP8 training and inference that holds accuracy while capturing the speedup, using loss scaling and numeric validation. Use when moving a model off FP32 to run faster or fit in less memory and the result must stay correct.
- [model-parallelism](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/model-parallelism/SKILL.md): Split a model that will not fit on one GPU across devices with tensor, pipeline, and expert parallelism, choosing each split by its communication cost. Use when weights or activations exceed a single card and you must shard without stalling on the interconnect.
- [onnx-export-pipelines](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/onnx-export-pipelines/SKILL.md): Export a trained model to ONNX that runs portably across runtimes, closing operator gaps and proving numeric parity against the source framework. Use when a PyTorch or TensorFlow model must run outside its training stack and the export must be trusted, not just produced.
- [quantization-deployment](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/quantization-deployment/SKILL.md): Quantize a trained model to INT8 or INT4 for inference, calibrate the ranges, and gate the release on a measured quality regression. Use when serving needs lower latency and memory and you will spend effort keeping accuracy inside a defined budget.
- [tensor-core-utilization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/tensor-core-utilization/SKILL.md): Get matrix multiplies onto the tensor cores by fixing shapes, precision, and alignment, then measure that the cores actually fired. Use when a GEMM or attention kernel runs far below the card's advertised throughput and you suspect it fell back to the CUDA cores.
- [tensorrt-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/tensorrt-optimization/SKILL.md): Compile a trained model into a fast, GPU-specific TensorRT engine by controlling precision, defining dynamic shape profiles, and proving the fused engine kept its accuracy. Use when a PyTorch or ONNX model must reach a hardware latency floor that eager execution cannot.
- [triton-inference-server](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/triton-inference-server/SKILL.md): Deploy models on NVIDIA Triton with a valid model repository, ensemble pipelines, and concurrent execution tuned to keep the GPU saturated. Use when serving one or more models through Triton and configuring layout, dynamic batching, instance groups, or a preprocess-plus-inference pipeline.
- [vllm-serving](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/gpu-ai-infrastructure/vllm-serving/SKILL.md): Deploy an LLM on vLLM with continuous batching, deliberate VRAM planning, and multi-model hosting that never overcommits the card. Use when serving on vLLM and deciding memory fraction, context length, tensor parallel size, and how many models share a GPU.
## Skills: i18n-localization
- [character-encoding](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/character-encoding/SKILL.md): Handle Unicode end to end so text survives storage, transport, and display without mojibake or truncation mid-character. Use when text arrives corrupted, lengths behave oddly, or emoji break a field.
- [currency-localization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/currency-localization/SKILL.md): Display, store, and reason about money across currencies without rounding errors or implied conversions. Use when showing prices in more than one currency or storing monetary amounts.
- [locale-aware-sorting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/locale-aware-sorting/SKILL.md): Sort and compare text using locale collation rather than byte order, so lists read correctly in every language. Use when displaying sorted names, searching case-insensitively, or matching user input.
- [locale-fallback](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/locale-fallback/SKILL.md): Define what a user sees when a string, a locale, or a region is not available, so gaps degrade predictably instead of showing keys or blanks. Use when supporting partial translations or regional variants.
- [locale-formatting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/locale-formatting/SKILL.md): Format numbers, dates, currency, and units by locale using the platform formatter rather than string templates. Use when displaying any value whose written form differs between regions.
- [plural-and-gender-rules](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/plural-and-gender-rules/SKILL.md): Handle plurals, grammatical gender, and agreement using locale plural categories rather than an if-else on count. Use when a string contains a number or refers to a person or object with gender.
- [pseudo-localization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/pseudo-localization/SKILL.md): Test localisation readiness with generated pseudo-translations that expand, accent, and bracket text, before any real translation exists. Use when preparing a product for translation and wanting to find breakage early.
- [rtl-layout](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/rtl-layout/SKILL.md): Support right-to-left languages by mirroring layout, icons, and interactions while leaving numbers and code untouched. Use when adding Arabic, Hebrew, Persian, or Urdu support to an interface.
- [string-externalization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/string-externalization/SKILL.md): Move user-facing text out of code into catalogs with stable keys and context, so translation becomes possible without touching logic. Use when preparing a product for translation or fixing hardcoded strings.
- [text-expansion-layout](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/text-expansion-layout/SKILL.md): Design interfaces that survive translated text growing or shrinking substantially, without truncation or broken layout. Use when building UI that will be translated, or fixing clipped text in another language.
- [translation-quality-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/translation-quality-review/SKILL.md): Review translated text for accuracy, register, and fit in context, with a rubric rather than an impression. Use when accepting translations or diagnosing why a localised product feels wrong to native speakers.
- [translation-workflow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/i18n-localization/translation-workflow/SKILL.md): Run translation as a pipeline with catalogs, context, review, and continuous updates rather than a one-off handoff. Use when shipping in multiple languages on an ongoing release cadence.
## Skills: javascript-typescript
- [js-async-patterns](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/js-async-patterns/SKILL.md): Compose async JavaScript with promises and async/await correctly, propagating errors and cancelling with AbortController. Use when writing async code, running work concurrently, or debugging swallowed errors and unhandled rejections.
- [js-error-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/js-error-handling/SKILL.md): Handle errors in JavaScript and TypeScript with proper Error subclasses, cause chains, and a policy for async and unhandled failures. Use when designing error handling or debugging lost stack traces and swallowed errors.
- [js-event-loop](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/js-event-loop/SKILL.md): Reason about the JavaScript event loop, microtasks vs macrotasks, and why blocking it freezes everything. Use when debugging ordering surprises, UI jank, or code that runs in an unexpected sequence.
- [js-immutability](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/js-immutability/SKILL.md): Work with immutable data in JavaScript through structural updates, readonly types, and freeze where it earns its cost. Use when managing shared or reactive state, or debugging bugs from unexpected mutation.
- [js-modules](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/js-modules/SKILL.md): Navigate ESM and CommonJS, interop between them, and structure imports so bundlers can tree-shake. Use when hitting module-resolution errors, mixing ESM and CJS, or shrinking a bundle.
- [js-tooling-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/js-tooling-selection/SKILL.md): Choose the JavaScript/TypeScript bundler, test runner, and linter for a project by its type, not by fashion. Use when setting up a toolchain or deciding whether to migrate an existing one.
- [monorepo-workspaces](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/monorepo-workspaces/SKILL.md): Run a JavaScript/TypeScript monorepo with workspaces, task orchestration, and internal package versioning that scales. Use when managing multiple packages in one repo or when a growing monorepo's builds and installs get slow.
- [node-backend-setup](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/node-backend-setup/SKILL.md): Bootstrap a Node.js backend with ESM, typed config, graceful shutdown, and structured logging from the start. Use when starting a Node service or hardening one that grew without foundations.
- [npm-publishing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/npm-publishing/SKILL.md): Publish an npm package that installs and imports cleanly: correct exports map, dual formats, types, and semver. Use when releasing a library to npm or fixing a package consumers cannot import.
- [ts-api-types](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/ts-api-types/SKILL.md): Type the boundaries of a TypeScript codebase: public API surfaces, branded types, and runtime validation of untyped input. Use when designing types others consume, or when external data enters your program.
- [tsconfig-mastery](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/tsconfig-mastery/SKILL.md): Configure tsconfig.json deliberately: the flags that matter, module and target settings, and build vs typecheck configs. Use when setting up TypeScript compilation or debugging confusing module and output errors.
- [typescript-generics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/typescript-generics/SKILL.md): Write TypeScript generics that infer well and stay readable, and know when a generic is not worth it. Use when designing typed reusable functions or APIs, or untangling generic signatures nobody can read.
- [typescript-narrowing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/typescript-narrowing/SKILL.md): Narrow union types safely with guards, discriminated unions, and exhaustiveness checks. Use when working with values that could be several types, or when the compiler will not let you access a property you know is there.
- [typescript-strictness](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/javascript-typescript/typescript-strictness/SKILL.md): Turn on and migrate to TypeScript's strict flags incrementally so the compiler catches real bugs. Use when configuring TypeScript strictness or tightening a loose codebase without a big-bang rewrite.
## Skills: jvm-dotnet
- [csharp-linq](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/csharp-linq/SKILL.md): Use LINQ with deferred execution understood, database translation respected, and loops chosen when they win. Use when writing C# queries over collections or ORMs, or debugging surprising LINQ behavior.
- [dotnet-async](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/dotnet-async/SKILL.md): Write async C# that never blocks on tasks, flows cancellation everywhere, and uses ValueTask where it pays. Use when writing .NET async code or debugging thread-pool starvation and deadlocks.
- [dotnet-dependency-injection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/dotnet-dependency-injection/SKILL.md): Use .NET's built-in DI with correct lifetimes, the options pattern, and constructor injection free of service-locator drift. Use when wiring .NET services or debugging captive-dependency and disposal bugs.
- [dotnet-minimal-apis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/dotnet-minimal-apis/SKILL.md): Build ASP.NET Core minimal APIs with organized endpoint groups, filters, typed results, and a clear line to MVC. Use when structuring .NET HTTP services or deciding between minimal APIs and controllers.
- [java-collections](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/java-collections/SKILL.md): Select Java collections by access pattern, use streams where they clarify, and default to immutability and records. Use when modeling data in Java or reviewing collection-heavy code.
- [jvm-gc-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/jvm-gc-selection/SKILL.md): Choose and size a JVM garbage collector from latency goals and allocation behavior, and read GC logs before tuning flags. Use when configuring JVM services or diagnosing pause and memory pressure problems.
- [jvm-memory-model](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/jvm-memory-model/SKILL.md): Apply happens-before reasoning, volatile, and safe publication to write correct concurrent Java/Kotlin. Use when writing shared-state JVM code or diagnosing visibility and reordering bugs.
- [jvm-profiling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/jvm-profiling/SKILL.md): Profile JVM services with async-profiler and JFR, separating CPU, allocation, and lock evidence, safely in production. Use when a JVM service is slow, hot, or memory-hungry and you need the cause.
- [kotlin-idioms](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/kotlin-idioms/SKILL.md): Write Kotlin that uses null safety, data classes, and coroutines as designed, with clean Java interop. Use when writing Kotlin or migrating Java code and habits to it.
- [spring-boot-discipline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/jvm-dotnet/spring-boot-discipline/SKILL.md): Keep Spring Boot apps explicit with constructor injection, typed configuration, test slices, and restrained magic. Use when building or reviewing Spring Boot services that must stay debuggable.
## Skills: learning-and-teaching
- [chess-improvement](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/chess-improvement/SKILL.md): Improve at chess through tactical pattern training, endgame fundamentals, and engine-assisted analysis of your own losses. Use when your rating has plateaued and playing more games is not helping.
- [curriculum-sequencing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/curriculum-sequencing/SKILL.md): Order material so each piece is learnable when it arrives, with prerequisites satisfied and difficulty increasing gradually. Use when designing a course, onboarding path, or tutorial series.
- [deliberate-practice](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/deliberate-practice/SKILL.md): Improve at a skill through focused repetition at the edge of ability with immediate feedback, rather than through accumulated hours. Use when you have plateaued despite continued practice.
- [explaining-to-beginners](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/explaining-to-beginners/SKILL.md): Explain something to someone with no background, without condescension and without jargon that quietly requires prior knowledge. Use when writing introductory material or onboarding someone new.
- [feedback-for-learning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/feedback-for-learning/SKILL.md): Give feedback that improves performance, timed and framed so it is used rather than defended against. Use when coaching, reviewing work, or mentoring.
- [knowledge-transfer](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/knowledge-transfer/SKILL.md): Move understanding from one person to others so critical knowledge does not leave with them. Use before someone changes role or when one person is the only one who understands something.
- [learning-from-failure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/learning-from-failure/SKILL.md): Extract the lesson from a mistake by examining the reasoning that produced it, rather than only the outcome. Use after something goes wrong, personally or as a team.
- [mental-model-building](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/mental-model-building/SKILL.md): Build an internal model of how a system works so you can predict its behaviour rather than recalling procedures. Use when learning a complex system or when you can follow steps but cannot debug.
- [self-directed-learning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/self-directed-learning/SKILL.md): Learn something substantial without a course, by defining the goal, finding the right resources, and building feedback into the process. Use when you need a capability nobody is going to teach you.
- [skill-assessment](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/skill-assessment/SKILL.md): Judge someone's ability, including your own, through demonstrated performance rather than confidence or credentials. Use when hiring, mentoring, or deciding what to learn next.
- [spaced-repetition](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/spaced-repetition/SKILL.md): Schedule review at increasing intervals so knowledge is retained with minimal total time. Use when you must remember material long-term rather than pass an immediate test.
- [teaching-technical-concepts](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/learning-and-teaching/teaching-technical-concepts/SKILL.md): Explain a technical idea by starting from what the learner knows, one concept at a time, with a concrete example before the abstraction. Use when teaching, mentoring, or writing an explanation.
## Skills: llm-engineering
- [agent-memory](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/agent-memory/SKILL.md): Design memory for an AI agent so it recalls what matters and forgets the rest, without drowning in its own history. Use when adding persistence, context recall, or long-running state to an agent.
- [agentic-loops](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/agentic-loops/SKILL.md): Build reliable agent loops (plan, act, observe) with termination, error recovery, and progress guarantees. Use when building an LLM agent that takes multiple tool-using steps toward a goal.
- [coding-agent-workflow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/coding-agent-workflow/SKILL.md): Direct and supervise a coding agent (Claude Code, Cursor, Antigravity) so it ships correct, verified work. Use when delegating engineering tasks to an AI agent and you want reliable results, not plausible-looking ones.
- [context-engineering](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/context-engineering/SKILL.md): Assemble what goes into an LLM's context on each call: selecting, ordering, and formatting the right information. Use when deciding what to put in a prompt or debugging why a model ignores or misuses provided information.
- [context-window-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/context-window-management/SKILL.md): Budget tokens across system prompt, history, and retrieval, with compaction that keeps what matters. Use when building long-running LLM applications or debugging context overflow and mid-conversation amnesia.
- [conversation-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/conversation-design/SKILL.md): Design multi-turn conversational systems with state tracking, memory injection, topic handling, and repair. Use when building chat assistants or fixing bots that forget, drift, or trap users.
- [embeddings-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/embeddings-selection/SKILL.md): Choose embedding models and chunking by evaluating retrieval on your own corpus, not by leaderboard rank. Use when building semantic search or RAG and deciding how to embed and chunk.
- [fine-tuning-vs-prompting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/fine-tuning-vs-prompting/SKILL.md): Decide between prompting, retrieval, and fine-tuning with eval-first discipline and honest data requirements. Use when someone proposes fine-tuning or a prompt has hit its ceiling.
- [goal-driven-execution](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/goal-driven-execution/SKILL.md): Pursue a high-level goal to completion autonomously: lock the done-condition, decompose, execute with verification, adapt, and know when to stop. Use when an agent is handed an outcome to achieve rather than a step to perform.
- [llm-cost-latency](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/llm-cost-latency/SKILL.md): Cut LLM cost and latency with caching, model tiering, prompt diet, batching, and streaming UX. Use when the inference bill or response time needs engineering down.
- [llm-eval-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/llm-eval-design/SKILL.md): Build LLM evaluations from real failures with calibrated judges and regression gates that catch quality drift. Use when an LLM feature needs quality measurement or prompts change without anyone knowing what broke.
- [llm-guardrails](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/llm-guardrails/SKILL.md): Layer input filtering, output validation, injection defense, and human escalation around LLM features. Use when an LLM system faces untrusted input or its outputs carry real-world consequences.
- [llm-observability](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/llm-observability/SKILL.md): Instrument LLM applications with request tracing, token accounting, quality signals, and feedback loops. Use when running LLM features in production or debugging why quality or cost moved.
- [mcp-server](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/mcp-server/SKILL.md): Design a Model Context Protocol server that exposes tools and data to AI agents safely and legibly. Use when building an MCP server or deciding what to expose to an agent.
- [prompt-caching](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/prompt-caching/SKILL.md): Cut LLM cost and latency by caching stable prompt prefixes, structuring prompts so the cache actually hits. Use when the same system prompt, tools, or examples repeat across calls and cost or time-to-first-token matters.
- [prompt-engineering](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/prompt-engineering/SKILL.md): Build prompts that get accurate, reliably-shaped output from any LLM, choosing the right technique for the task. Use when writing, improving, or debugging a prompt.
- [rag-pipeline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/rag-pipeline/SKILL.md): Design a retrieval-augmented generation pipeline that answers from sources and can be trusted. Use when building or debugging RAG: chunking, embedding, retrieval, context assembly, and grounding.
- [retrieval-reranking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/retrieval-reranking/SKILL.md): Improve RAG answer quality by reranking retrieved candidates so the most relevant chunks reach the model. Use when a retrieval system returns roughly-right documents but the best ones are not on top, or answers miss available evidence.
- [self-reflection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/self-reflection/SKILL.md): Have an agent critique and improve its own output before delivering, catching errors a first pass misses, without spiraling. Use when correctness matters and an agent should check its own work rather than ship the first draft.
- [staying-on-task](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/staying-on-task/SKILL.md): Keep an AI agent anchored to the actual goal through long or messy work. Use at the start of any multi-step task, and whenever work begins to drift, balloon, or stall.
- [structured-output](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/structured-output/SKILL.md): Get valid structured data from LLMs with schema-constrained generation, boundary validation, and repair loops. Use when LLM output feeds code, databases, or downstream systems.
- [tool-use-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/llm-engineering/tool-use-design/SKILL.md): Design LLM tools with descriptions that steer, granularity that composes, and error returns the model can act on. Use when building agent tool sets or debugging wrong-tool and wrong-argument failures.
## Skills: machine-learning
- [cross-validation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/cross-validation/SKILL.md): Pick CV schemes that respect time and grouping, nest them for tuning, and read the variance, not just the mean. Use when data is too small for a single split or when validating tuning claims.
- [drift-monitoring](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/drift-monitoring/SKILL.md): Detect input, prediction, and performance drift with reference windows and act through retrain or rollback triggers. Use when operating models in production or diagnosing gradual quality decay.
- [experiment-tracking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/experiment-tracking/SKILL.md): Record every training run's code, data, config, and results so any model is reproducible and comparisons are honest. Use when setting up ML experiment infrastructure or untangling which run produced the prod model.
- [feature-engineering](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/feature-engineering/SKILL.md): Build features that are leakage-free, temporally correct, and reproducible between training and serving. Use when creating model inputs or auditing a suspiciously good offline score.
- [hyperparameter-tuning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/hyperparameter-tuning/SKILL.md): Search hyperparameters with budgets, early stopping, and validation hygiene so gains are real, not overfit to the dev set. Use when tuning models or reviewing tuning claims.
- [imbalanced-data](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/imbalanced-data/SKILL.md): Handle skewed classes with threshold moving, weighting, and PR-based evaluation instead of reflexive resampling. Use when the positive class is rare and accuracy looks deceptively high.
- [ml-baselines](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/ml-baselines/SKILL.md): Establish heuristic and simple-model baselines that bound what complexity is worth. Use when starting any ML project or auditing whether a complex model earns its cost.
- [ml-error-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/ml-error-analysis/SKILL.md): Review model errors by hand, discover failing slices, and decide whether data or model fixes pay more. Use when a model underperforms and you need to know why before spending compute.
- [ml-problem-framing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/ml-problem-framing/SKILL.md): Frame ML problems around a decision, a measurable target, and honest error costs before touching models. Use when scoping an ML project or reviewing whether one should exist.
- [model-deployment](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/model-deployment/SKILL.md): Ship models through batch, online, or edge patterns with shadow testing, gated rollouts, and rollback. Use when moving a model to production or designing the serving architecture.
- [model-evaluation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/model-evaluation/SKILL.md): Evaluate models with cost-aligned metrics, slice analysis, calibration, and uncertainty, not a single accuracy number. Use when choosing evaluation metrics or judging whether a model is fit to ship.
- [train-test-discipline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/machine-learning/train-test-discipline/SKILL.md): Split data before looking at it, respect time and groups, and quarantine the test set so scores mean something. Use when setting up ML evaluation or auditing why offline metrics did not survive production.
## Skills: marketing
- [community-led-growth](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/community-led-growth/SKILL.md): Grow through a community that supports and advocates for itself, with genuine investment rather than extraction. Use when the product benefits from peer knowledge and users want to talk to each other.
- [competitive-messaging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/competitive-messaging/SKILL.md): Talk about competitors accurately and fairly in a way that helps buyers decide, without claims you cannot support. Use when buyers ask how you compare or a competitor is winning deals.
- [content-marketing-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/content-marketing-strategy/SKILL.md): Plan content that reaches buyers at the moment they are looking, with a cadence you can sustain and a way to tell whether it worked. Use when publishing sporadically without knowing whether it helps.
- [conversion-rate-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/conversion-rate-optimization/SKILL.md): Improve the proportion of visitors who take the desired action, through evidence about where they drop rather than opinions about design. Use when traffic is adequate and conversion is not.
- [customer-personas](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/customer-personas/SKILL.md): Build audience profiles from evidence rather than imagination, capturing the job, the trigger, and the objection. Use when marketing targets everyone and converts nobody.
- [email-marketing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/email-marketing/SKILL.md): Run lifecycle and campaign email that people open, with segmentation, timing, and permission handled properly. Use when email is a channel you own and want to keep.
- [launch-marketing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/launch-marketing/SKILL.md): Coordinate a launch so attention arrives when the product is ready and converts rather than dissipating. Use when releasing something significant enough to warrant a moment.
- [marketing-attribution](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/marketing-attribution/SKILL.md): Assign credit for conversions across touchpoints honestly, knowing what each model hides. Use when deciding where to spend and channels each claim the same conversions.
- [paid-acquisition](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/paid-acquisition/SKILL.md): Buy traffic profitably by measuring against payback and lifetime value rather than cost per click. Use when considering paid channels or when spend is rising without profit.
- [positioning-and-messaging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/positioning-and-messaging/SKILL.md): Decide what you are, who for, and against what alternative, then say it in words customers use. Use when nobody can explain the product in one sentence or the same product is described differently everywhere.
- [retention-marketing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/retention-marketing/SKILL.md): Keep and re-engage existing customers, which is usually cheaper and more valuable than acquiring new ones. Use when churn is high or growth is entirely dependent on new acquisition.
- [social-media-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/marketing/social-media-strategy/SKILL.md): Choose platforms and a cadence you can sustain, with content native to each rather than cross-posted. Use when social presence is scattered and producing nothing.
## Skills: mcp
- [mcp-authentication](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-authentication/SKILL.md): Authenticate and authorise access to a remote MCP server so tools act as the right user with the least necessary privilege. Use when hosting an MCP server that more than one person or agent reaches.
- [mcp-client-integration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-client-integration/SKILL.md): Connect MCP servers into an application with lifecycle management, capability negotiation, and graceful degradation when a server is unavailable. Use when building a client or embedding MCP into a product.
- [mcp-context-budgeting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-context-budgeting/SKILL.md): Keep tool results small enough that an agent can hold what matters, through pagination, projection, and summarisation at the server. Use when tool output floods the context window.
- [mcp-error-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-error-handling/SKILL.md): Return errors an agent can act on, distinguishing retryable failures from permanent ones and never leaking internals. Use when building MCP tools that will fail in production.
- [mcp-multi-server-orchestration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-multi-server-orchestration/SKILL.md): Run an agent across several MCP servers without name collisions, tool overload, or ambiguity about which server owns an action. Use when one agent connects to more than a few servers.
- [mcp-prompt-templates](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-prompt-templates/SKILL.md): Ship reusable prompt templates from an MCP server so users invoke tested workflows rather than improvising. Use when a server supports a workflow that benefits from a known-good prompt.
- [mcp-resource-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-resource-design/SKILL.md): Expose data through MCP resources with stable URIs, useful listings, and sizes that fit a context window. Use when an agent needs to read data rather than perform an action.
- [mcp-sampling-and-elicitation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-sampling-and-elicitation/SKILL.md): Use server-initiated model calls and user prompts responsibly, so a server can ask for reasoning or input without seizing control. Use when a server needs the model's help or a decision from the user mid-operation.
- [mcp-security-boundaries](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-security-boundaries/SKILL.md): Treat tool output as untrusted data, confirm destructive actions, and keep an agent's reach inside what its user may do. Use when an MCP server touches real systems or reads content from outside your control.
- [mcp-server-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-server-testing/SKILL.md): Test an MCP server for protocol conformance, tool selection accuracy, and behaviour under real model calls rather than only unit tests. Use before shipping a server others will connect agents to.
- [mcp-tool-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-tool-design/SKILL.md): Design MCP tools an agent can select correctly, with names, descriptions, and schemas that make the right call obvious and the wrong one impossible. Use when exposing capability to an agent through an MCP server.
- [mcp-transport-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mcp/mcp-transport-selection/SKILL.md): Choose between local stdio and remote HTTP transports for an MCP server based on trust, deployment, and who runs it. Use when deciding how a server will be hosted and reached.
## Skills: media-processing
- [audio-processing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/audio-processing/SKILL.md): Normalise, compress, and prepare audio for reliable playback and transcription, handling levels and formats consistently. Use when accepting recorded audio or producing spoken content.
- [document-parsing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/document-parsing/SKILL.md): Extract text and structure from PDFs, office documents, and scans reliably enough to search, index, or summarise. Use when users upload documents whose contents the product must understand.
- [format-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/format-selection/SKILL.md): Choose media formats and codecs by compatibility, quality, and licensing, with fallbacks for what the client cannot play. Use when deciding what to store and deliver.
- [media-delivery](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/media-delivery/SKILL.md): Serve media efficiently with caching, range requests, and access control, so playback starts fast and private files stay private. Use when media is slow to load or must be restricted to authorised users.
- [media-processing-queue](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/media-processing-queue/SKILL.md): Run transcoding, thumbnailing, and extraction as queued background work with progress, retries, and failure visibility. Use when media processing takes long enough that it cannot happen in the request.
- [media-storage-tiering](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/media-storage-tiering/SKILL.md): Match storage class to access pattern so rarely read media costs less without becoming unavailable. Use when media storage cost grows faster than usage.
- [metadata-stripping](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/metadata-stripping/SKILL.md): Remove embedded metadata such as location, device, and author from user files before they are stored or shared. Use when users upload photographs or documents that others will see.
- [resumable-uploads](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/resumable-uploads/SKILL.md): Let large uploads survive network interruption by chunking and resuming from the last confirmed part. Use when files are large enough that a failed upload is a real cost to the user.
- [thumbnail-generation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/thumbnail-generation/SKILL.md): Produce preview images for files of every type, consistently sized and generated without blocking the user. Use when a file list or gallery needs visual previews.
- [upload-pipeline-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/upload-pipeline-design/SKILL.md): Move a file from the user's device to durable storage and a processed state, with validation, progress, and recovery at every stage. Use when building any feature that accepts files.
- [video-transcoding](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/media-processing/video-transcoding/SKILL.md): Convert uploaded video into the renditions needed for reliable playback across devices and bandwidths. Use when accepting user video or delivering video that must play everywhere.
## Skills: mobile
- [app-store-readiness](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/app-store-readiness/SKILL.md): Pass App Store and Play review on the first attempt and recover fast from rejections. Use when preparing a mobile submission, writing store metadata, or responding to a review rejection.
- [deep-linking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/deep-linking/SKILL.md): Set up universal and app links that open the right in-app screen from a URL, with deferred links surviving install and a routing layer that validates every parameter. Use when adding shareable links, wiring campaign or email links into the app, or debugging links that open the browser instead.
- [mobile-input-ux](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/mobile-input-ux/SKILL.md): Make mobile forms and controls fast to use with correct keyboards, reachable touch targets, and restrained haptics. Use when building input-heavy mobile screens or fixing form abandonment on small screens.
- [mobile-navigation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/mobile-navigation/SKILL.md): Structure mobile navigation with a clear stack, tab, and modal hierarchy and a back stack that survives deep links and process death. Use when designing app navigation, adding a deep-link target, or fixing lost-state and wrong-back-button bugs.
- [mobile-observability](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/mobile-observability/SKILL.md): Instrument mobile apps for crash-free rate, ANR and hang detection, and release health you can gate rollouts on. Use when setting up mobile monitoring or deciding whether a release is healthy enough to expand.
- [mobile-performance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/mobile-performance/SKILL.md): Make a mobile app fast where users feel it by protecting startup time, keeping lists at frame rate, handling images at display size, and keeping work off the main thread. Use when the app is slow to open, scrolling janks, or the UI freezes during work.
- [mobile-release-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/mobile-release-strategy/SKILL.md): Ship mobile releases through phased rollouts with hotfix paths and a forced-upgrade policy that never strands users. Use when planning app releases, a rollout gate, or recovery from a bad build in the stores.
- [offline-first-mobile](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/offline-first-mobile/SKILL.md): Build a mobile app where the local database is the source of truth, the UI reads and writes it directly, and a background sync engine reconciles with the server. Use when the app must work on flaky or no connectivity, or when network-coupled screens feel slow and fragile.
- [push-notifications](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/push-notifications/SKILL.md): Deliver mobile push that users keep enabled by asking permission at the right moment, managing token lifecycle, using categories and silent pushes correctly, and respecting quiet hours. Use when adding push, debugging non-delivery, or opt-in rates are low.
- [react-native-architecture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/mobile/react-native-architecture/SKILL.md): Structure React Native apps around clear native-module boundaries and decide honestly when RN fits. Use when starting or auditing a React Native codebase, or weighing RN against fully native development.
## Skills: multi-agent-teams
- [agent-accountability-loop](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-accountability-loop/SKILL.md): Track every commitment from assignment to completion, chasing what is late and escalating what is stuck, so work finishes rather than fading. Use when things are agreed in meetings and quietly never happen.
- [agent-analytics-desk](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-analytics-desk/SKILL.md): Turn business data into answered questions with agents that define the metric, pull it consistently, check it against a second source, and state what it does not prove. Use when numbers are quoted in meetings that nobody can reproduce.
- [agent-arch-board](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-arch-board/SKILL.md): Run an architecture board of agents where one proposes a design, several review it independently and blind, and a chair synthesizes a binding decision. Use when a design choice matters enough that one agent's opinion will not do and you want independent scrutiny before committing.
- [agent-blackboard-workspace](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-blackboard-workspace/SKILL.md): Coordinate agents through a shared written workspace they each read and update, instead of passing messages. Use when several agents contribute to one artefact over time and message passing loses state.
- [agent-board-reporting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-board-reporting/SKILL.md): Assemble an investor or board update from source metrics with agents that draft, fact-check every number, and surface bad news rather than bury it. Use when periodic reporting eats days and the numbers keep needing correction.
- [agent-brand-guardian](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-brand-guardian/SKILL.md): Keep every outgoing artefact consistent in voice, claims, and terminology with agents that check against a written brand definition. Use when output comes from many sources and the product sounds like several different companies.
- [agent-capacity-planning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-capacity-planning/SKILL.md): Know what the company can actually take on this cycle, in agent budget and human hours, and refuse work beyond it. Use when everything is committed and nothing finishes.
- [agent-chief-of-staff](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-chief-of-staff/SKILL.md): Run the management layer above specialist desks: set the week's priorities, route work, chase what is stuck, and end every cycle with decisions and owners. Use when several agent desks exist but nothing coordinates them into finished work.
- [agent-code-review-loop](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-code-review-loop/SKILL.md): Run an author agent and a reviewer agent in a loop with a strict finding format, a mandatory verification pass, and a convergence rule that ends it. Use when you want agent-to-agent code review that improves the diff instead of spinning forever on style or re-flagging fixed issues.
- [agent-company-blueprint](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-company-blueprint/SKILL.md): Compose specialist agent desks into one operating company with a shared ledger, a weekly cadence, and human approval gates on anything binding. Use when you want agents to run the recurring operations of a business rather than a single project.
- [agent-competitive-analysis-team](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-competitive-analysis-team/SKILL.md): Run competitive analysis as agents that tear down assigned competitors on one template, enforce sourcing rules, and synthesize implications for your product. Use when you want a market landscape built by a coordinated agent team rather than one agent skimming marketing sites.
- [agent-compliance-desk](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-compliance-desk/SKILL.md): Run continuous compliance with agents that map controls to evidence, collect it on a schedule, and flag drift before an audit finds it. Use when preparing for or maintaining a certification and evidence gathering is a periodic fire drill.
- [agent-content-newsroom](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-content-newsroom/SKILL.md): Run a publishing cadence with agents that plan a calendar, research and draft against a brief, fact-check claims, and queue posts for human approval. Use when content output is sporadic and quality varies with whoever wrote it.
- [agent-context-isolation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-context-isolation/SKILL.md): Give each agent in a system only the context it needs, so failures stay contained and context stays clean. Use when designing a multi-agent system and deciding what each agent sees and shares.
- [agent-crisis-comms](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-crisis-comms/SKILL.md): Prepare public communication during an incident with agents that assemble facts, draft holding statements, and check for claims that cannot be supported, while a human speaks. Use when something has gone wrong publicly and the response must be fast and accurate.
- [agent-customer-success-team](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-customer-success-team/SKILL.md): Run retention as a standing function with agents that watch usage signals, spot churn risk early, prepare account reviews, and hand humans a specific reason to reach out. Use when customers leave without warning and renewals are handled reactively.
- [agent-data-team](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-data-team/SKILL.md): Run a data team as agents that build the pipeline, gate on quality checks, run the analysis, and independently audit every headline metric. Use when you want a number produced by a coordinated agent team rather than one agent's unverified query.
- [agent-debate-protocol](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-debate-protocol/SKILL.md): Have agents argue opposing positions from the same evidence, then synthesize, so the strongest case for each option is heard before deciding. Use when a decision is genuinely contested and one agent's answer would hide the trade-off.
- [agent-decision-log](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-decision-log/SKILL.md): Record what was decided, by whom, on what basis, and when to revisit, so decisions are not relitigated or silently forgotten. Use when the same discussion recurs and nobody remembers why the current approach was chosen.
- [agent-delegation-protocol](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-delegation-protocol/SKILL.md): Decide what to hand to an agent, what to keep with a human, and what to split, based on reversibility and consequence rather than capability alone. Use when deciding how much of a workflow to automate.
- [agent-dependency-manager](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-dependency-manager/SKILL.md): Track cross-desk and external dependencies so blocked work is visible early and the blocker has an owner. Use when work stalls waiting on somebody else and nobody notices until the deadline.
- [agent-design-review-panel](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-design-review-panel/SKILL.md): Convene several reviewer agents with fixed distinct lenses, correctness, security, cost, and simplicity, then synthesize their verdicts into one. Use when a single review agent keeps missing whole classes of problems because it cannot hold every concern at once on a design or plan.
- [agent-docs-guild](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-docs-guild/SKILL.md): Run a team of documentation agents that finds the gaps, drafts the pages, gets them reviewed against the code, and sweeps for staleness on a schedule. Use when a codebase has outrun its docs and you need both new coverage and a way to stop pages from rotting.
- [agent-ensemble-voting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-ensemble-voting/SKILL.md): Run the same task several times independently and combine the results by agreement, to damp variance on judgement calls. Use when output varies between runs and being consistently right matters more than being fast.
- [agent-escalation-ladder](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-escalation-ladder/SKILL.md): Define what gets escalated, to whom, and how fast, so problems reach a decision maker at the right moment rather than too early or too late. Use when issues either sit unresolved or interrupt the wrong people constantly.
- [agent-executive-briefing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-executive-briefing/SKILL.md): Produce a short honest briefing across every desk on a fixed cadence, surfacing decisions needed rather than activity performed. Use when leading a business through agent desks and needing one readable view.
- [agent-finance-desk](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-finance-desk/SKILL.md): Run a standing finance function with agents that reconcile transactions, track runway, flag anomalies, and prepare reporting for a human to approve. Use when the money side of a business needs steady attention rather than a quarterly scramble.
- [agent-fundraising-room](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-fundraising-room/SKILL.md): Prepare a raise with agents that assemble the narrative, stress-test it as an investor would, and organise diligence material, while the founder owns every conversation. Use when preparing to raise and the story keeps changing between meetings.
- [agent-generate-and-verify](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-generate-and-verify/SKILL.md): Pair every generating agent with an independent verifier whose only job is to refute the output, so plausible-but-wrong work is caught before it ships. Use when an agent's output will be acted on and being wrong is expensive.
- [agent-goal-cascade](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-goal-cascade/SKILL.md): Translate company objectives into desk-level goals and weekly work, keeping the line from a task to the objective visible. Use when teams are busy but nobody can say how the work serves the goal.
- [agent-growth-team](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-growth-team/SKILL.md): Run a team of growth agents that designs an experiment, builds the variant, analyzes the result, and passes an ethics gate before anything ships. Use when you want product changes tested rigorously instead of shipped on a hunch, with a guardrail against manipulative tactics.
- [agent-handoff-protocol](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-handoff-protocol/SKILL.md): Design each handoff between two agents as an explicit artifact contract with a context budget and a rule for what must survive the crossing. Use when work passes from one agent to the next and the receiver keeps losing constraints, re-deriving decisions, or drowning in raw transcript.
- [agent-hiring-panel](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-hiring-panel/SKILL.md): Simulate an interview panel as agents that design questions, score independently on anchored rubrics, and reconcile in a debrief. Use when you want to pressure-test a hiring loop, calibrate rubrics, or dry-run questions, not to score a real candidate.
- [agent-human-checkpoint](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-human-checkpoint/SKILL.md): Place human approval at the points where being wrong is expensive or irreversible, with enough context to decide quickly. Use when agents perform work that has real consequences.
- [agent-incident-response-team](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-incident-response-team/SKILL.md): Replicate a live incident team as agents with a commander, parallel investigators, comms, and a scribe, coordinated on a fixed cadence. Use when you want an outage worked by a coordinated agent team instead of one agent debugging alone.
- [agent-iterative-refinement](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-iterative-refinement/SKILL.md): Improve output through repeated critique and revision against a fixed standard, stopping when the standard is met or gains stop. Use when first-pass output is close but not good enough and the quality bar is writable.
- [agent-legal-desk](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-legal-desk/SKILL.md): Use agents to triage contracts and policies, extract obligations, flag unusual terms, and prepare a lawyer's review rather than replace it. Use when routine agreements pile up and nothing is tracked after signature.
- [agent-loop-until-exhausted](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-loop-until-exhausted/SKILL.md): Keep running discovery rounds until several consecutive rounds find nothing new, rather than stopping at a fixed count. Use when searching for an unknown number of items such as bugs, risks, or edge cases.
- [agent-map-reduce](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-map-reduce/SKILL.md): Split a large task across parallel agents that each handle one slice, then merge their outputs deliberately. Use when the work exceeds one context window or would take too long serially.
- [agent-marketing-studio](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-marketing-studio/SKILL.md): Produce campaigns with agents that research the audience, draft variants against a brief, check claims and brand voice, and leave publishing to a human. Use when marketing output is inconsistent or bottlenecked on one person writing everything.
- [agent-meeting-runner](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-meeting-runner/SKILL.md): Prepare, run, and close meetings with agents so each one produces decisions and owned actions instead of discussion. Use when meetings consume time and nothing is decided or recorded.
- [agent-migration-crew](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-migration-crew/SKILL.md): Run a team of migration agents that inventories the work, transforms each slice in isolation, verifies it, and merges under strict discipline. Use when a large mechanical change like a framework bump, an API rename, or a schema move spans many files and one agent would lose the thread or break main.
- [agent-oncall-triage](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-oncall-triage/SKILL.md): Run alert triage as agents that dedup the storm, rate severity by user impact, match a runbook, and draw a hard human-escalation line. Use when you want incoming alerts sorted and enriched by an agent team before they reach the on-call engineer.
- [agent-ops-command](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-ops-command/SKILL.md): Run the daily operating rhythm with agents that sweep every system each morning, surface what needs a decision, and keep nothing waiting silently. Use when running a business day to day and things fall through the cracks between desks.
- [agent-orchestration-antipatterns](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-orchestration-antipatterns/SKILL.md): Guard a multi-agent team against the structural failures single agents never hit: context lost across handoffs, false agreement, and runaway cost. Use when a team costs more than one agent or trusts its own output, and you need to find out why.
- [agent-partnerships-desk](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-partnerships-desk/SKILL.md): Research, qualify, and prepare partnership approaches with agents, leaving the relationship and the commitment to a human. Use when business development is ad hoc and partner conversations start without preparation.
- [agent-people-ops-desk](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-people-ops-desk/SKILL.md): Support the recurring people function with agents that maintain onboarding paths, keep policy documents current, prepare review inputs, and flag gaps, while every human decision stays human. Use when a growing team keeps reinventing process.
- [agent-plan-execute-replan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-plan-execute-replan/SKILL.md): Separate planning from execution and replan when reality diverges, so a long task does not follow a plan that stopped being true. Use when work has many steps and early assumptions are likely to be wrong.
- [agent-pm-eng-loop](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-pm-eng-loop/SKILL.md): Pair a product-manager agent with engineer agents through spec, pushback, scope negotiation, and acceptance so the build matches intent. Use when an agent team must turn a fuzzy request into a shipped, accepted increment.
- [agent-postmortem-council](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-postmortem-council/SKILL.md): Run a team of postmortem agents that builds the timeline, analyzes causes, drafts corrective actions, and reviews for blamelessness and completeness. Use after an incident when you need a rigorous, blameless writeup and owned action list instead of a hasty narrative that pins it on a person.
- [agent-pricing-committee](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-pricing-committee/SKILL.md): Convene agents to model pricing options, argue them from customer, competitor, and margin angles, and hand a human a decision pack. Use when setting or changing prices and the discussion keeps going in circles.
- [agent-procurement-desk](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-procurement-desk/SKILL.md): Evaluate vendors with agents that build a comparable requirement matrix, research each option, check security and data terms, and prepare a recommendation for human sign-off. Use when choosing tools or suppliers and comparisons keep drifting on vendor marketing.
- [agent-progressive-disclosure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-progressive-disclosure/SKILL.md): Give agents context in stages, escalating to more capable models or fuller context only when the cheap path proves insufficient. Use when most tasks are easy but a few are hard and cost or latency matters.
- [agent-qa-gate](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-qa-gate/SKILL.md): Place a QA agent as the last blocking node before output ships, checking acceptance criteria against executed test evidence with the power to veto. Use when builder agents keep declaring done on work that does not meet its criteria and you need one gate that runs the artifact instead of trusting the claim.
- [agent-quality-council](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-quality-council/SKILL.md): Hold a consistent standard across everything a company ships, with agents that review against written criteria and escalate disagreements rather than averaging them. Use when quality varies by who happened to do the work.
- [agent-red-team-blue-team](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-red-team-blue-team/SKILL.md): Run attacker and defender agents in a fix-and-re-attack loop so exploitable bugs get found, triaged, fixed, and verified before ship. Use when you want a system probed and hardened by an agent team rather than one pass of review.
- [agent-release-train](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-release-train/SKILL.md): Run release agents that draft the changelog, scan risk, verify the candidate, and gate publish behind a go/no-go check. Use when cutting a release and you want the boring parts automated and the risky parts caught before ship.
- [agent-research-lab](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-research-lab/SKILL.md): Run a lab of researcher agents that search in parallel, verify sources independently, and synthesize a cited answer. Use when a question needs breadth of sources and every load-bearing claim must trace to evidence.
- [agent-risk-register](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-risk-register/SKILL.md): Maintain a living register of business risks with agents that surface new ones, track mitigations, and force stale entries back to a decision. Use when risks are discussed in meetings and then forgotten until they happen.
- [agent-role-definition](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-role-definition/SKILL.md): Write role cards that pin each agent to one charter with declared inputs, outputs, refusal rules, and non-overlapping scope. Use when assembling a multi-agent team and you need every agent to stay in its lane instead of all drifting toward the same work.
- [agent-sales-pipeline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-sales-pipeline/SKILL.md): Staff a pipeline with agents that research accounts, qualify leads against explicit criteria, draft outreach for human sending, and keep the CRM honest. Use when lead flow needs consistent handling and the pipeline record keeps rotting.
- [agent-security-audit-team](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-security-audit-team/SKILL.md): Run a security audit as agents that map the attack surface, review each surface in parallel, skeptic-test every finding, and assemble one report. Use when you want a codebase audited by a coordinated agent team instead of a single review pass.
- [agent-specialist-router](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-specialist-router/SKILL.md): Route each request to the agent best suited to it, with a fallback and an explicit unknown path, instead of one generalist handling everything. Use when tasks vary enough that one prompt serves none of them well.
- [agent-startup-squad](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-startup-squad/SKILL.md): Run a lean startup team of agents (builder, marketer, analyst) through one disciplined weekly loop of ship, promote, and measure. Use when you want a small agent team to move a single product metric week over week.
- [agent-status-rollup](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-status-rollup/SKILL.md): Aggregate desk-level state into an honest company view where problems stay visible instead of averaging away. Use when everything is reported green and things are still going wrong.
- [agent-strategy-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-strategy-review/SKILL.md): Run a periodic strategy review with agents that check whether stated goals still match reality, argue the alternatives, and force an explicit continue or change decision. Use when quarterly planning repeats last quarter's plan by default.
- [agent-support-desk](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-support-desk/SKILL.md): Run a team of support agents that triages each ticket, reproduces the problem, drafts a reply, and hands clean escalations to a human. Use when inbound support volume needs consistent handling and a person must approve every customer-facing reply before it goes out.
- [agent-tournament-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-tournament-selection/SKILL.md): Generate several independent attempts, score them against explicit criteria, and select or combine the winner, instead of iterating one attempt. Use when the solution space is wide and the first approach may not be the best.
- [agent-training-academy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-training-academy/SKILL.md): Turn internal knowledge into role-based learning paths with agents that build, test, and keep material current as systems change. Use when onboarding is slow because knowledge lives in people rather than in material.
- [agent-vendor-operations](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-vendor-operations/SKILL.md): Track every vendor's cost, renewal, usage, and access with agents that flag waste and surface renewals before they auto-renew. Use when software spend grows quietly and nobody knows what is still in use.
- [agent-work-assignment](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-work-assignment/SKILL.md): Match work to the agent or person best able to finish it, with explicit capacity limits so nothing is assigned into an already full queue. Use when work is distributed by whoever is nearest rather than by fit and capacity.
- [agent-workload-balancing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/agent-workload-balancing/SKILL.md): Redistribute work across desks and workers as load shifts, so one bottleneck does not stall the company while others idle. Use when some desks are overwhelmed and others have nothing queued.
- [virtual-engineering-team](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/multi-agent-teams/virtual-engineering-team/SKILL.md): Run a product-engineering squad of agents from spec to shipped change with a PM, an architect, two engineers, a reviewer, and QA. Use when a task is too large for one agent and needs both division of labor and an independent quality gate.
## Skills: networking
- [dns-fundamentals](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/networking/dns-fundamentals/SKILL.md): Reason about DNS records, resolution, TTLs, and caching so name changes land predictably instead of mysteriously. Use when configuring a domain, moving a service, or debugging why a hostname resolves to the wrong place.
- [load-balancing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/networking/load-balancing/SKILL.md): Distribute traffic across instances with the right algorithm, health checks, and draining so capacity is used and failures are absorbed. Use when scaling a service horizontally or diagnosing uneven load.
- [tls-and-certificates](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/networking/tls-and-certificates/SKILL.md): Issue, install, renew, and debug TLS certificates so connections stay encrypted and trusted without surprise expiry. Use when setting up HTTPS, rotating a certificate, or diagnosing a trust or handshake error.
- [websockets-at-scale](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/networking/websockets-at-scale/SKILL.md): Run persistent connections with heartbeats, reconnection, backpressure, and fan-out that survive load and restarts. Use when building realtime features on WebSockets or a similar long-lived transport.
## Skills: notifications-messaging
- [delivery-tracking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/delivery-tracking/SKILL.md): Know whether a message was accepted, delivered, opened, and acted on, and treat failures as events rather than statistics. Use when messages are assumed delivered and support tickets say otherwise.
- [digest-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/digest-design/SKILL.md): Batch many low-urgency events into one periodic summary that is worth opening, rather than sending each as it happens. Use when individual events are too frequent or too minor to interrupt.
- [email-deliverability](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/email-deliverability/SKILL.md): Get email into the inbox rather than the spam folder, through authentication, reputation, and list hygiene. Use when email is not arriving or engagement suddenly drops.
- [in-app-messaging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/in-app-messaging/SKILL.md): Deliver messages inside the product where they are contextual and non-interruptive, using the right surface for each urgency. Use when a message relates to what the user is doing right now.
- [multi-channel-orchestration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/multi-channel-orchestration/SKILL.md): Coordinate across push, email, in-app, and SMS so a user gets one message rather than the same thing four times. Use when several channels exist and users receive duplicates.
- [notification-batching](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/notification-batching/SKILL.md): Group related events so a burst of activity produces one message instead of twenty, with rules that stay predictable. Use when a single action generates many notifications or activity comes in bursts.
- [notification-fatigue](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/notification-fatigue/SKILL.md): Detect and reverse the point where users stop reading, by measuring engagement decay and cutting volume before they mute. Use when open rates are falling or mute rates are rising.
- [notification-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/notification-strategy/SKILL.md): Decide what deserves a notification, on which channel, and at what urgency, before building any of it. Use when notifications are added per feature and users are starting to mute everything.
- [push-notification-permissions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/push-notification-permissions/SKILL.md): Ask for push permission at a moment when the value is obvious, and handle denial gracefully, because the prompt only comes once. Use when adding push to a mobile or web product.
- [quiet-hours-and-timing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/quiet-hours-and-timing/SKILL.md): Send at times that respect the recipient's local hours and working pattern, deferring anything non-urgent. Use when notifications reach people at night or on weekends.
- [transactional-messaging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/transactional-messaging/SKILL.md): Send the messages a user is waiting for, such as receipts, resets, and confirmations, with reliability and clarity that marketing messages do not need. Use when building password resets, receipts, or order confirmations.
- [unsubscribe-and-preferences](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/notifications-messaging/unsubscribe-and-preferences/SKILL.md): Give users real control over what they receive, with granular options and an honest one-click exit. Use when building preference centres or reducing complaint rates.
## Skills: open-source
- [code-of-conduct-enforcement](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/code-of-conduct-enforcement/SKILL.md): Apply a code of conduct consistently, with a reporting path, proportionate responses, and records, so it protects people rather than decorating the repository. Use when adopting a code of conduct or handling a report.
- [contributor-onboarding](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/contributor-onboarding/SKILL.md): Lower the cost of a first contribution with a working setup, a clear scope, and a fast review so people come back. Use when a project wants contributors and gets drive-by patches or none.
- [documentation-for-adoption](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/documentation-for-adoption/SKILL.md): Write the docs that decide whether someone adopts a project: a truthful readme, a working quickstart, and answers to the first questions. Use when a project is capable but nobody gets past the first ten minutes.
- [forking-and-vendoring](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/forking-and-vendoring/SKILL.md): Decide between patching upstream, forking, and vendoring a dependency, and carry the ongoing cost knowingly. Use when a dependency needs a change you cannot get merged, or is unmaintained.
- [issue-triage](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/issue-triage/SKILL.md): Process incoming issues so real problems get found fast and the queue stays honest about what will be worked on. Use when an issue tracker has grown past what anyone reads.
- [maintainer-sustainability](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/maintainer-sustainability/SKILL.md): Keep a project alive without burning out its maintainers, through scope limits, shared load, and honest signals about capacity. Use when maintenance feels like an obligation you cannot decline.
- [open-source-licensing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/open-source-licensing/SKILL.md): Choose a licence, comply with the licences you depend on, and keep attribution correct as a project grows. Use when publishing a project, adding a dependency, or answering whether a licence permits your use.
- [project-governance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/project-governance/SKILL.md): Define who decides what in a project, how that changes, and how disputes end, before a disagreement forces the question. Use when a project grows past one maintainer or a conflict has no clear resolution path.
- [release-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/release-management/SKILL.md): Ship releases on a predictable rhythm with versioned changes, tested artifacts, and notes users can act on. Use when releases are ad hoc or users cannot tell what changed.
- [semantic-versioning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/semantic-versioning/SKILL.md): Communicate compatibility through version numbers so consumers know what upgrading costs. Use when releasing a library, deciding whether a change is breaking, or setting a dependency range.
- [supply-chain-security](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/supply-chain-security/SKILL.md): Protect a project and its users from compromised dependencies, publishing credentials, and build pipelines. Use when publishing packages or auditing what your build actually trusts.
- [vulnerability-disclosure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/open-source/vulnerability-disclosure/SKILL.md): Receive, triage, fix, and announce security reports on a coordinated timeline that protects users. Use when running a project that could have security issues, or when you receive a report.
## Skills: payments-billing
- [failed-payment-recovery](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/failed-payment-recovery/SKILL.md): Recover revenue from failed recurring charges with retries, clear notice, and a graceful path back, without harassing customers. Use when involuntary churn from card failures is material.
- [invoicing-and-receipts](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/invoicing-and-receipts/SKILL.md): Produce invoices and receipts that are accurate, immutable, and contain what tax authorities and customers require. Use when billing businesses or operating where invoices are legally regulated.
- [payment-idempotency](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/payment-idempotency/SKILL.md): Make payment operations safe to retry so a network timeout never charges a customer twice. Use when calling a payment API, processing webhooks, or building any money-moving endpoint.
- [payment-integration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/payment-integration/SKILL.md): Integrate a payment provider so charges are authorised, confirmed, and recorded correctly even when the customer closes the tab. Use when adding checkout or moving to a new payment provider.
- [payment-reconciliation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/payment-reconciliation/SKILL.md): Match provider settlements against your own records so every charge, fee, refund, and payout is accounted for. Use when closing books, chasing a discrepancy, or building financial reporting.
- [pci-scope-reduction](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/pci-scope-reduction/SKILL.md): Keep card data out of your systems so compliance obligations stay minimal, and know what remains in scope when it cannot. Use when handling card payments or preparing for a compliance assessment.
- [pricing-change-migration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/pricing-change-migration/SKILL.md): Change prices or plan structure without breaking trust or billing, deciding who moves, when, and with what notice. Use when raising prices, restructuring plans, or retiring a legacy tier.
- [refunds-and-disputes](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/refunds-and-disputes/SKILL.md): Handle refunds, chargebacks, and disputes with evidence, deadlines, and a policy applied consistently. Use when building refund flows or responding to a chargeback.
- [revenue-recognition-basics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/revenue-recognition-basics/SKILL.md): Understand why cash collected is not revenue earned, and record deferred revenue so financial reporting reflects delivery. Use when building billing data models or reporting on a subscription business.
- [subscription-billing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/subscription-billing/SKILL.md): Model recurring plans, cycles, upgrades, and cancellations so what a customer is charged always matches what they agreed to. Use when building or changing recurring billing.
- [tax-calculation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/tax-calculation/SKILL.md): Determine, apply, and record sales tax or VAT correctly by jurisdiction, product type, and customer status. Use when selling across borders or when tax handling is currently a flat assumption.
- [usage-based-metering](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/payments-billing/usage-based-metering/SKILL.md): Meter consumption accurately enough to bill on it, with reconciliation, limits, and transparency the customer can verify. Use when charging by usage rather than a flat subscription.
## Skills: performance
- [algorithmic-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/algorithmic-optimization/SKILL.md): Replace a hot algorithm with one of better complexity, a fitter data structure, or memoized results instead of micro-tuning the slow one. Use when a profiler points at a function whose cost is inherent to its approach, not to constant-factor waste.
- [async-io-patterns](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/async-io-patterns/SKILL.md): Structure async code so the event loop stays free, slow producers apply backpressure, and blocking calls never stall unrelated work. Use when writing or debugging async IO and throughput is low, latency is spiky, or the loop appears to hang.
- [batching-and-debouncing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/batching-and-debouncing/SKILL.md): Coalesce a flood of small operations into fewer larger ones with batch windows, debounce, or throttle, chosen by whether you need the last event or a steady rate. Use when high-frequency triggers each do expensive work: per-keystroke queries, per-event writes, per-scroll handlers.
- [benchmark-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/benchmark-design/SKILL.md): Write benchmarks that do not lie, controlling warmup, isolation, and statistics so the number reflects the code and not the environment. Use when comparing implementations, defending a performance claim, or a microbenchmark result looks too good.
- [big-o-in-practice](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/big-o-in-practice/SKILL.md): Apply complexity analysis where input size actually makes it decide performance, and ignore it where constant factors dominate. Use when choosing an algorithm or data structure and you need to know whether asymptotic cost or the real constant is what bites.
- [bundle-size](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/bundle-size/SKILL.md): Shrink JavaScript bundles by analyzing what ships, enabling real tree shaking, splitting heavy code, and putting the dependency list on a diet. Use when the initial JS payload is large, slow to parse, or growing unchecked.
- [cache-invalidation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/cache-invalidation/SKILL.md): Keep cached data correct as the source changes using write-through, event-driven eviction, and versioned keys. Use when a cache exists and stale reads are a risk, or when users report seeing old data after a write.
- [caching-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/caching-strategy/SKILL.md): Decide what to cache and where by choosing layers, key shapes, and TTLs against the read pattern and freshness need. Use when reads are hot and repeated and you are deciding whether and where to add a cache before writing invalidation code.
- [cdn-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/cdn-strategy/SKILL.md): Push work to the edge so requests never touch your origin, using cache headers, invalidation, and origin shielding. Use when origin load is high, global latency is uneven, or a CDN sits in front of your app but barely caches.
- [compression-tradeoffs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/compression-tradeoffs/SKILL.md): Choose a compression codec and level by weighing size reduction against CPU cost, and place compression where the bytes are actually scarce. Use when deciding whether and how to compress payloads, logs, or stored data, or when compression is burning CPU for little gain.
- [concurrency-tuning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/concurrency-tuning/SKILL.md): Size worker pools, queue depths, and batch widths against the real bottleneck so parallelism adds throughput instead of contention. Use when a parallel job stops scaling, saturates a resource, or spends more time coordinating than working.
- [connection-pooling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/connection-pooling/SKILL.md): Size connection pools from throughput and latency math, then monitor for saturation and set timeout policy so a slow dependency fails fast instead of hanging. Use when a service exhausts database connections, requests queue for a connection, or pool size was picked by guess.
- [cpu-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/cpu-optimization/SKILL.md): Speed up a CPU-bound hot path by fixing its algorithm and memory access first, then applying micro-optimization only where the profiler still points. Use when a function dominates CPU time and you need it faster without changing what it computes.
- [font-loading](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/font-loading/SKILL.md): Load web fonts without layout shift by subsetting the file, setting font-display, preloading first-paint weights, and matching fallback metrics. Use when custom fonts cause invisible text, a flash of restyle, or a CLS spike.
- [gc-tuning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/gc-tuning/SKILL.md): Cut garbage-collection pauses and overhead by lowering allocation rate, sizing the heap, and reading pause logs before touching a flag. Use when a managed-runtime service shows latency spikes, high CPU in GC, or out-of-memory errors under load.
- [http-caching](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/http-caching/SKILL.md): Use HTTP caching correctly with etags, max-age, and stale-while-revalidate so clients and proxies reuse responses without serving stale data. Use when responses lack cache headers, a bad deploy served stale content, or revalidation traffic is heavy.
- [image-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/image-optimization/SKILL.md): Serve right-sized images by encoding modern formats, generating responsive srcset widths, and deferring offscreen decode while prioritizing the hero. Use when images are the heaviest bytes on a page or the LCP element loads slowly.
- [io-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/io-optimization/SKILL.md): Reduce input/output cost by cutting round trips, moving fewer bytes, and turning random access into sequential access. Use when a workload is IO-bound: disk, network, or syscall overhead dominates while the CPU sits idle.
- [lazy-loading](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/lazy-loading/SKILL.md): Defer expensive work until the moment it is actually needed, so startup stays fast and unused paths cost nothing. Use when initialization is slow, a page ships code it never runs, or a list renders far more rows than the screen shows.
- [materialized-views](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/materialized-views/SKILL.md): Precompute expensive read queries into materialized views and pick a refresh strategy that fits a stated staleness budget. Use when an aggregate or join is read far more than the underlying data changes and recomputing it per request is too slow.
- [memory-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/memory-optimization/SKILL.md): Cut a program's memory footprint by fixing data layout, reusing allocations, and streaming input instead of buffering it whole. Use when a process is killed by the OOM killer, garbage collection dominates the profile, or heap growth tracks input size.
- [n-plus-one-queries](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/n-plus-one-queries/SKILL.md): Find and eliminate N+1 database access where one query per row replaces one query for the set, using eager loading, batching, or a dataloader. Use when a list endpoint is slow, query counts scale with result size, or an ORM lazy-loads inside a loop.
- [pagination-performance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/pagination-performance/SKILL.md): Paginate large result sets so page cost stays constant by using keyset (cursor) pagination instead of OFFSET, with a stable, encoded cursor. Use when deep pages get slow, an infinite scroll drifts or duplicates rows, or OFFSET grows with page depth.
- [performance-budgets](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/performance-budgets/SKILL.md): Set numeric performance budgets and enforce them in CI so regressions fail the build instead of reaching users. Use when performance keeps sliding release over release or a team wants to hold a latency or bundle target.
- [performance-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/performance-optimization/SKILL.md): Make code measurably faster by profiling first and fixing the actual bottleneck. Use when something is slow, uses too much memory, or needs to handle more load.
- [serialization-performance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/serialization-performance/SKILL.md): Cut the CPU and bytes spent turning objects into wire or disk format by choosing the right format, reusing schemas and buffers, and avoiding copies. Use when serialization shows up in the profile, payloads are large, or encode/decode latency dominates a hot request path.
- [startup-time](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/startup-time/SKILL.md): Cut startup latency by deferring heavy imports, precompiling ahead of time, and pruning the dependency tree that loads before first useful work. Use when CLI launch, serverless cold start, or dev-loop boot time is too slow.
- [web-vitals](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/performance/web-vitals/SKILL.md): Improve LCP, CLS, and INP by measuring field data, tracing each metric to its specific cause, and applying the fixes known to move that number. Use when Core Web Vitals are failing or a page feels slow to load, settle, or respond.
## Skills: platform-engineering
- [build-system-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/build-system-design/SKILL.md): Design builds that are fast, reproducible, and cacheable, so developers wait less and CI costs less. Use when builds are slow, flaky, or produce different results locally and in CI.
- [developer-productivity-metrics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/developer-productivity-metrics/SKILL.md): Measure the system's throughput and stability rather than individual output, and use the numbers to remove friction. Use when improving engineering effectiveness or justifying platform work.
- [environment-provisioning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/environment-provisioning/SKILL.md): Create development, preview, and staging environments that resemble production closely enough to be useful, and clean them up automatically. Use when environments drift, cost too much, or block testing.
- [golden-path-templates](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/golden-path-templates/SKILL.md): Provide starting templates that encode the organisation's defaults so new services are consistent without anyone reading a standards document. Use when new services vary widely in structure and quality.
- [internal-developer-platform](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/internal-developer-platform/SKILL.md): Build a platform that lets product teams ship without filing tickets, treating the platform as a product with users. Use when infrastructure work is a bottleneck or every team solves the same problems differently.
- [local-development-setup](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/local-development-setup/SKILL.md): Make a working local environment reachable in minutes from a clean machine, and keep it close to production. Use when onboarding takes days or developers cannot run the system locally.
- [paved-road-adoption](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/paved-road-adoption/SKILL.md): Get teams onto the supported path through incentives and migration support rather than mandates. Use when a better platform exists and teams are not moving to it.
- [platform-abstractions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/platform-abstractions/SKILL.md): Choose the level of abstraction a platform exposes so it hides complexity without hiding what teams need to control. Use when designing platform interfaces or when teams keep bypassing them.
- [platform-as-product](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/platform-as-product/SKILL.md): Run an internal platform with users, feedback, and adoption metrics rather than as a mandated standard. Use when platform adoption is poor or teams complain about the tools they are required to use.
- [policy-as-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/policy-as-code/SKILL.md): Express organisational rules as automated checks in the pipeline rather than as documents people are meant to follow. Use when standards exist on paper and are inconsistently applied.
- [self-service-infrastructure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/self-service-infrastructure/SKILL.md): Let teams provision what they need within guardrails, without waiting for an infrastructure team to act. Use when provisioning requests queue and infrastructure work is reactive.
- [service-catalog](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/platform-engineering/service-catalog/SKILL.md): Maintain an inventory of services with owners, dependencies, and operational metadata so questions about who owns what are answerable. Use when nobody can say who owns a service or what depends on it.
## Skills: product-management
- [ab-test-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/ab-test-design/SKILL.md): Design product experiments with real hypotheses, honest sample-size math, guardrails, and peeking discipline. Use when validating a change by experiment or reviewing a test before believing its result.
- [customer-interviews](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/customer-interviews/SKILL.md): Run user interviews that surface past behavior instead of polite predictions, recruited and synthesized honestly. Use when gathering qualitative evidence for product decisions.
- [feature-sunsetting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/feature-sunsetting/SKILL.md): Remove features with usage evidence, migration paths, and staged communication that preserves trust. Use when retiring product surface or making the case that something should die.
- [mvp-scoping](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/mvp-scoping/SKILL.md): Scope minimum viable products around the riskiest assumption, cut to learn fast, and hold an explicit quality floor. Use when defining a first version or rescuing an MVP that grew into a v3.
- [prioritization-frameworks](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/prioritization-frameworks/SKILL.md): Prioritize with RICE-class scoring applied honestly, cost of delay, and refusals that carry reasons. Use when ordering a roadmap or defending priority calls under stakeholder pressure.
- [product-discovery](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/product-discovery/SKILL.md): Validate problems before building solutions using evidence standards and opportunity mapping. Use when deciding what to build next or challenging a solution that arrived before its problem.
- [product-launch](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/product-launch/SKILL.md): Launch features through tiered rollouts, a readiness checklist, coordinated comms, and a post-launch review. Use when shipping something users will notice or coordinating a cross-team release moment.
- [product-metrics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/product-metrics/SKILL.md): Choose a north star with input metrics you can move, guardrails you must not break, and defenses against vanity. Use when defining product measurement or auditing a dashboard full of numbers nobody acts on.
- [roadmap-communication](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/roadmap-communication/SKILL.md): Communicate roadmaps with now/next/later horizons, honest commitment levels, and audience-shaped views. Use when publishing product direction or managing the fallout of roadmap changes.
- [user-story-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/product-management/user-story-writing/SKILL.md): Write user stories around outcomes with testable acceptance criteria, sliced thin enough to ship in days. Use when turning product intent into buildable work or fixing a backlog of vague tickets.
## Skills: project-management
- [cross-team-coordination](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/cross-team-coordination/SKILL.md): Keep work moving across team boundaries with explicit interfaces, owners, and shared checkpoints. Use when a project spans teams and progress stalls at handoffs.
- [milestone-planning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/milestone-planning/SKILL.md): Break a project into milestones that each prove something, so progress is verifiable rather than asserted. Use when a project is long enough that the end is not visible from the start.
- [project-closure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/project-closure/SKILL.md): End a project deliberately, with handover, documentation, and a decision about what happens to what was built. Use when a project reaches its goal or is being stopped.
- [project-kickoff](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/project-kickoff/SKILL.md): Start a project with shared understanding of goal, roles, and working agreements, so early ambiguity does not become late rework. Use at the start of any multi-person project.
- [project-retrospective](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/project-retrospective/SKILL.md): Review a completed project to extract what should change next time, focusing on systems rather than individuals. Use at the end of a project or a significant phase.
- [project-risk-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/project-risk-management/SKILL.md): Identify what could derail a project, decide responses in advance, and track them rather than reacting when they happen. Use at project start and at every major checkpoint.
- [project-scoping](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/project-scoping/SKILL.md): Define what a project includes, excludes, and depends on before work starts, so scope disagreements surface early. Use when starting a project or when a project keeps growing.
- [project-status-reporting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/project-status-reporting/SKILL.md): Report progress in a form that surfaces problems early and lets a reader act, rather than reassuring. Use when reporting to sponsors or across teams.
- [resource-planning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/resource-planning/SKILL.md): Match people and capacity to project needs over time, accounting for partial allocation, ramp-up, and the cost of splitting attention. Use when planning who works on what across projects.
- [schedule-and-critical-path](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/schedule-and-critical-path/SKILL.md): Sequence work by dependency to find which tasks actually determine the finish date, and manage those. Use when a project has many parallel workstreams and an immovable date.
- [scope-change-control](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/project-management/scope-change-control/SKILL.md): Handle new requests mid-project by making the trade-off visible rather than absorbing them silently. Use when a project is accumulating additions and the date is not moving.
## Skills: prompt-writing
- [chain-of-thought-prompting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/chain-of-thought-prompting/SKILL.md): Ask a model to reason before answering when the task needs intermediate steps, and know when it costs more than it gives. Use for multi-step reasoning, and avoid it for simple retrieval or formatting.
- [context-placement](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/context-placement/SKILL.md): Decide where in a prompt to put documents, history, and instructions, given that models attend unevenly across a long context. Use when prompts are long and the model ignores material in the middle.
- [few-shot-examples](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/few-shot-examples/SKILL.md): Teach a task by showing worked examples, chosen and ordered so the model generalises the pattern rather than copying the specifics. Use when instructions alone produce inconsistent format or judgement.
- [negative-instructions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/negative-instructions/SKILL.md): Tell a model what not to do in a way that works, by converting prohibitions into positive alternatives wherever possible. Use when a prompt lists things to avoid and the model keeps doing them.
- [output-format-control](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/output-format-control/SKILL.md): Get output in exactly the structure downstream code expects, using schemas, examples, and validation rather than hope. Use when a model's output is parsed by a program rather than read by a person.
- [prompt-constraints](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/prompt-constraints/SKILL.md): Express limits on length, scope, style, and behaviour so they are followed rather than politely ignored. Use when a model consistently exceeds bounds or drifts outside the task.
- [prompt-iteration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/prompt-iteration/SKILL.md): Improve a prompt through controlled changes measured against a fixed set of cases, rather than by rewriting until an example looks good. Use when a prompt underperforms and each edit is a guess.
- [prompt-structure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/prompt-structure/SKILL.md): Order a prompt so the model knows its task, its material, and its output before it starts generating. Use when writing any non-trivial prompt or fixing one that produces the wrong shape of answer.
- [prompt-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/prompt-testing/SKILL.md): Test prompts like code, with a case set, pass criteria, and regression runs on every change including model upgrades. Use when a prompt is in production and its behaviour matters.
- [prompt-versioning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/prompt-versioning/SKILL.md): Manage prompts as versioned artefacts with review, rollback, and a record of what changed and why. Use when prompts affect production behaviour and more than one person edits them.
- [role-and-persona-prompting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/role-and-persona-prompting/SKILL.md): Assign a role to shape expertise, register, and priorities, without pretending it grants knowledge the model lacks. Use when output should read as written by a particular kind of expert for a particular audience.
- [system-prompt-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/prompt-writing/system-prompt-design/SKILL.md): Write the durable instructions that shape every turn, covering role, boundaries, and defaults without micromanaging each response. Use when configuring an assistant or agent that will handle many different requests.
## Skills: python
- [pytest-mastery](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/pytest-mastery/SKILL.md): Structure pytest suites with fixtures, parametrize, and markers so tests stay fast, isolated, and readable. Use when writing Python tests or untangling a slow, fixture-heavy suite.
- [python-asyncio](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-asyncio/SKILL.md): Decide whether asyncio pays off, keep the event loop unblocked, and structure concurrency with TaskGroup and disciplined cancellation. Use when writing async Python or diagnosing a hung, slow, or silently-failing event loop.
- [python-cli-tools](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-cli-tools/SKILL.md): Build Python command-line tools with correct exit codes, stream discipline, and a distributable entry point. Use when writing or packaging a CLI in Python.
- [python-concurrency](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-concurrency/SKILL.md): Choose threads, processes, or asyncio from workload shape, and use concurrent.futures without deadlocks. Use when parallelizing Python work or debugging concurrency that is slower than sequential.
- [python-dataclasses](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-dataclasses/SKILL.md): Choose between dataclass, NamedTuple, and pydantic, and configure frozen, slots, and validation correctly. Use when modeling structured data in Python or reviewing class boilerplate.
- [python-decorators](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-decorators/SKILL.md): Write decorators that preserve signatures and compose cleanly, including parameterized and class-applied forms. Use when adding cross-cutting behavior to Python functions or fixing decorator-related introspection breakage.
- [python-environments](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-environments/SKILL.md): Pick an environment manager, pin dependencies with a lockfile, and produce reproducible installs that never touch system Python. Use when setting up a project's dependencies, fixing "works on my machine", or hardening CI installs.
- [python-error-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-error-handling/SKILL.md): Design exception hierarchies, catch narrowly, and preserve error context so failures stay diagnosable. Use when structuring errors in a Python library or application, or cleaning up broad except blocks.
- [python-generators](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-generators/SKILL.md): Build lazy pipelines with generators and itertools, trading materialized lists for constant memory, and know when eager evaluation is the right call. Use when processing streams, large or infinite sequences, or composing data transformations.
- [python-packaging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-packaging/SKILL.md): Package a Python project with a single pyproject.toml, a src layout, and a clean build/publish path to PyPI including entry points. Use when turning a script or library into an installable, distributable package.
- [python-performance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-performance/SKILL.md): Profile first, then remove Python-level overhead through vectorization, better algorithms, or a compiled extension. Use when Python code is too slow and you must decide where and how to optimize.
- [python-project-structure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-project-structure/SKILL.md): Organize Python packages so imports stay clean, cycles cannot form, and the layout scales with the codebase. Use when starting a Python project or untangling circular imports and grab-bag modules.
- [python-typing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/python-typing/SKILL.md): Add type hints where they catch real errors and document contracts, choosing Protocol, generics, or TypedDict deliberately and setting a checker strictness you can actually hold. Use when introducing or tightening types on a Python codebase.
- [pythonic-idioms](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/python/pythonic-idioms/SKILL.md): Apply Python idioms where they cut bookkeeping and clarify intent, and refuse them where the clever form hides control flow. Use when writing loops, resource handling, or unpacking and deciding how idiomatic to make it.
## Skills: realtime-collaboration
- [collaborative-editing-models](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/collaborative-editing-models/SKILL.md): Choose between operational transformation, CRDTs, and locking for multi-user editing, and understand what each costs. Use when more than one person can edit the same document at the same time.
- [comments-and-annotations](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/comments-and-annotations/SKILL.md): Attach comments to content that keeps changing, so anchors survive edits and threads stay resolvable. Use when adding review, feedback, or discussion to a document or design.
- [conflict-resolution-ux](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/conflict-resolution-ux/SKILL.md): Present merge conflicts to users so they can resolve them confidently, rather than resolving silently and losing work. Use when concurrent edits cannot be merged automatically.
- [live-cursors-and-selection](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/live-cursors-and-selection/SKILL.md): Render other people's cursors and selections so they inform rather than distract, and stay correct as content changes. Use when showing where collaborators are working in a shared document.
- [offline-sync](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/offline-sync/SKILL.md): Let clients work disconnected and reconcile changes on reconnect without losing edits or resurrecting deletions. Use when building an application that must work on an unreliable network.
- [optimistic-ui-updates](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/optimistic-ui-updates/SKILL.md): Apply changes locally before the server confirms, then reconcile or roll back honestly when it does not. Use when latency makes a correct-but-slow interface feel broken.
- [presence-and-awareness](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/presence-and-awareness/SKILL.md): Show who is here, where they are, and what they are doing, at a cost that scales and without leaking more than intended. Use when adding cursors, avatars, or typing indicators to a shared surface.
- [realtime-data-sync](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/realtime-data-sync/SKILL.md): Keep client state current with server changes using subscriptions, deltas, and resync, without drift or memory growth. Use when a UI must reflect data that other users or systems are changing.
- [realtime-permissions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/realtime-permissions/SKILL.md): Enforce and revoke access on live connections so a permission change takes effect immediately rather than at the next page load. Use when shared documents have varying access levels.
- [realtime-scaling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/realtime-scaling/SKILL.md): Scale collaborative sessions across instances with room routing, shared state, and controlled fan-out. Use when one server can no longer hold all active sessions.
- [realtime-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/realtime-testing/SKILL.md): Test collaborative features against concurrency, reconnection, and ordering rather than only the single-user path. Use when a realtime feature works in development and breaks with real users.
- [version-history-ux](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/realtime-collaboration/version-history-ux/SKILL.md): Keep and present document history so users can see what changed, who changed it, and restore safely. Use when edits are shared or when accidental loss must be recoverable.
## Skills: reliability
- [capacity-forecasting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/capacity-forecasting/SKILL.md): Predict when current capacity will be exhausted and plan the increase before it becomes an incident. Use when growth is steady enough to plan for or when scaling events surprise you.
- [chaos-engineering](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/chaos-engineering/SKILL.md): Deliberately inject failures to verify that resilience mechanisms work before a real incident tests them. Use when a system has failover, retries, or redundancy that has never actually been exercised.
- [disaster-recovery-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/disaster-recovery-testing/SKILL.md): Verify that backups restore and failover works by practising it, rather than trusting that the procedure would work. Use when recovery has never been rehearsed end to end.
- [failure-mode-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/failure-mode-analysis/SKILL.md): Enumerate how a system can fail and what each failure does, before building the mitigations. Use when designing a critical system or reviewing one that has surprised you.
- [graceful-degradation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/graceful-degradation/SKILL.md): Design systems that lose functionality progressively rather than failing entirely when a dependency is unavailable. Use when one component's failure currently takes down the whole product.
- [incident-severity-levels](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/incident-severity-levels/SKILL.md): Classify incidents consistently so the response, communication, and escalation match the impact. Use when incident response is either overwhelming or too slow.
- [load-shedding](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/load-shedding/SKILL.md): Reject excess work deliberately under overload so the system serves some requests well instead of failing all of them. Use when traffic spikes cause complete collapse rather than partial service.
- [on-call-health](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/on-call-health/SKILL.md): Run an on-call rotation that is sustainable, with alert hygiene, fair distribution, and follow-through on what caused the pages. Use when on-call is dreaded or people are leaving because of it.
- [redundancy-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/redundancy-design/SKILL.md): Add redundancy where it removes a single point of failure, understanding what each level protects against and what it costs. Use when designing for availability targets.
- [reliability-tradeoffs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/reliability-tradeoffs/SKILL.md): Decide how much reliability to buy, given that each additional nine costs disproportionately more than the last. Use when reliability investment is being decided without reference to its cost.
- [service-level-objectives](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/service-level-objectives/SKILL.md): Define measurable reliability targets from the user's perspective and use the error budget to decide between shipping and stabilising. Use when reliability is debated without numbers.
- [toil-reduction](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/reliability/toil-reduction/SKILL.md): Identify repetitive manual operational work and eliminate it, so capacity goes to improvement rather than maintenance. Use when an on-call rotation is consumed by routine intervention.
## Skills: research
- [autonomous-research](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/autonomous-research/SKILL.md): Build and run an autonomous research agent that plans, searches, verifies, and synthesizes reliably, with the safeguards a naive research loop lacks. Use when an AI agent must research a question end to end without a human checking every step.
- [decision-journals](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/decision-journals/SKILL.md): Record decisions with their context and predictions to enable honest calibration and defeat hindsight bias. Use when making consequential decisions you want to learn from later.
- [deep-research](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/deep-research/SKILL.md): Run a thorough multi-source research investigation end to end: plan, search broadly, verify, and synthesize a cited answer. Use when a question needs deep, autonomous research across many sources, not a quick lookup.
- [estimation-techniques](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/estimation-techniques/SKILL.md): Estimate unknown quantities with Fermi decomposition, reference classes, and honest error bars. Use when you need a number for a decision and no exact figure exists.
- [experiment-design-basics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/experiment-design-basics/SKILL.md): Design experiments with controls, randomization, confound awareness, and pre-registered analysis. Use when testing a hypothesis empirically and needing the result to actually mean something.
- [fact-checking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/fact-checking/SKILL.md): Verify claims before stating them: trace to the source, corroborate independently, and separate fact from inference. Use when accuracy matters, especially before an agent asserts facts, numbers, or quotes.
- [first-principles-thinking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/first-principles-thinking/SKILL.md): Reason from fundamental truths by excavating assumptions and rebuilding from constraints, knowing when analogy is faster. Use when stuck in a solution space defined by convention or challenging an inherited assumption.
- [hypothesis-driven-work](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/hypothesis-driven-work/SKILL.md): Frame work as falsifiable hypotheses, test the cheapest first, and update on evidence rather than defending the plan. Use when facing uncertainty and tempted to build the whole thing before learning anything.
- [literature-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/literature-review/SKILL.md): Survey prior work systematically through search strategy, citation chasing, quality assessment, and synthesis. Use when entering a new domain or grounding a decision in what is already known.
- [reading-papers](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/reading-papers/SKILL.md): Read research papers efficiently in passes, separating claims from evidence and assessing reproducibility. Use when extracting value from academic papers without reading every one cover to cover.
- [research-planning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/research-planning/SKILL.md): Scope a research question, decide what evidence would answer it, and plan the search before diving in. Use when starting any research task, so effort goes to the questions that matter instead of wandering.
- [research-synthesis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/research-synthesis/SKILL.md): Turn multiple sources into a defensible, source-attributed answer that separates fact from inference. Use when researching a question across documents, articles, or search results.
- [source-evaluation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/source-evaluation/SKILL.md): Judge whether a source is credible and relevant: authority, evidence, bias, and recency. Use when deciding whether to trust and cite a source, in any research.
- [tradeoff-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/tradeoff-analysis/SKILL.md): Compare options with explicit weighted criteria, sensitivity checks, and reversibility awareness. Use when facing a consequential choice between alternatives with no obvious winner.
- [web-research](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/research/web-research/SKILL.md): Search the web effectively: query construction, iterating on results, and going to primary sources. Use when researching a topic online, especially for an agent gathering current or factual information.
## Skills: scripting-automation
- [automation-guardrails](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/automation-guardrails/SKILL.md): Put confirmation gates, blast-radius limits, audit trails, and kill switches around automation that can destroy things. Use when building scripts or bots with destructive power.
- [bash-robustness](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/bash-robustness/SKILL.md): Write bash that fails loudly, quotes correctly, cleans up after itself, and passes shellcheck. Use when writing shell scripts that automation or other people will depend on.
- [cli-ux-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/cli-ux-design/SKILL.md): Design command-line interfaces with predictable flags, honest exit codes, machine-readable modes, and helpful failure text. Use when building CLI tools people other than the author will run.
- [environment-config](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/environment-config/SKILL.md): Manage script and tool configuration through env vars, dotenv files, and layered precedence without leaking secrets. Use when wiring configuration for CLIs, scripts, and local development.
- [makefile-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/makefile-design/SKILL.md): Write Makefiles with honest dependencies, phony discipline, and self-documenting help, and know when make is the wrong tool. Use when standardizing project task-running or fixing rebuild bugs.
- [powershell-essentials](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/powershell-essentials/SKILL.md): Write PowerShell that leans on the object pipeline, handles errors deliberately, and runs cross-platform where needed. Use when automating Windows or writing pwsh scripts for mixed fleets.
- [scheduled-jobs](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/scheduled-jobs/SKILL.md): Run cron and timer jobs with overlap locks, jitter, missed-run policies, and monitoring for silent absence. Use when scheduling recurring automation or debugging jobs that overlap, pile up, or quietly stop.
- [script-idempotency](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/script-idempotency/SKILL.md): Write scripts whose reruns are always safe through check-then-act steps, atomic writes, and dry-run modes. Use when automation may run twice, die halfway, or need a safe retry.
- [shell-portability](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/shell-portability/SKILL.md): Write shell that runs across POSIX sh, bash versions, and GNU/BSD userlands, or decide deliberately not to. Use when scripts must run on multiple platforms, containers, or CI images.
- [text-processing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/scripting-automation/text-processing/SKILL.md): Choose grep, sed, awk, or jq by job, prefer structured formats, and know when a one-liner should become a script. Use when slicing logs, transforming files, or wrangling command output.
## Skills: search-relevance
- [autocomplete-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/autocomplete-design/SKILL.md): Suggest queries as the user types, fast enough to feel instant and relevant enough to be worth reading. Use when adding a search box that should guide rather than merely accept input.
- [faceted-search](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/faceted-search/SKILL.md): Provide filters that narrow results honestly, with counts that reflect what is actually available and a clear way back out. Use when a result set is large enough that browsing needs structure.
- [full-text-search-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/full-text-search-design/SKILL.md): Design a text search feature with the right analyzer, fields, and matching model so results are relevant rather than merely returned. Use when adding search to a product or replacing a LIKE query that no longer works.
- [hybrid-search](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/hybrid-search/SKILL.md): Combine keyword and vector retrieval so exact terms and semantic meaning both work, and fuse the two rankings sensibly. Use when keyword search misses paraphrases or vector search misses exact identifiers.
- [query-understanding](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/query-understanding/SKILL.md): Interpret what a user meant before matching, through normalisation, intent detection, and entity extraction. Use when queries are short, ambiguous, or full of product-specific language.
- [relevance-tuning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/relevance-tuning/SKILL.md): Improve ranking with a judged evaluation set and measured changes rather than intuition. Use when search feels wrong and every proposed fix is someone's opinion.
- [search-analytics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/search-analytics/SKILL.md): Instrument search so queries, clicks, and abandonment tell you what to fix. Use when improving relevance without evidence, or when nobody can say whether search works.
- [search-indexing-pipeline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/search-indexing-pipeline/SKILL.md): Get data into a search index reliably and keep it current, with reindexing, partial updates, and a defined staleness budget. Use when search results lag reality or a schema change requires a full rebuild.
- [search-result-presentation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/search-result-presentation/SKILL.md): Present results so a user can judge relevance without opening each one, with useful snippets, clear grouping, and honest metadata. Use when results are correct but users still cannot find what they need.
- [synonyms-and-stemming](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/synonyms-and-stemming/SKILL.md): Match words to their variants and equivalents without collapsing distinctions that matter. Use when searches miss obvious results, or when unrelated results appear because two words were merged.
- [typo-tolerance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/typo-tolerance/SKILL.md): Correct or forgive misspelled queries without turning precise searches into fuzzy guesses. Use when users mistype and get nothing, or when fuzzy matching returns irrelevant results.
- [zero-results-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/search-relevance/zero-results-handling/SKILL.md): Turn an empty result set into a useful next step instead of a dead end, and treat the query as a signal worth acting on. Use when searches return nothing and users leave.
## Skills: security
- [api-security](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/api-security/SKILL.md): Secure an API by enforcing per-object authorization, per-caller quota, and schema-validated input on every endpoint. Use when building or reviewing an HTTP or GraphQL API that serves authenticated users, machine clients, or partner integrations.
- [audit-logging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/audit-logging/SKILL.md): Record security-relevant events in a tamper-evident, append-only log that answers who did what and when. Use when building or reviewing logging for authentication, authorization, privilege changes, or access to sensitive data.
- [authn-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/authn-design/SKILL.md): Design sign-in so credentials are hashed with a slow algorithm, guessing is rate limited, and sessions rotate on login to defeat fixation. Use when building or reviewing registration, login, or password-reset flows.
- [authz-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/authz-design/SKILL.md): Enforce authorization so access is denied by default and every request re-checks that the caller owns the specific resource, closing IDOR gaps. Use when building endpoints that read or modify data belonging to a particular user or tenant.
- [browser-storage-safety](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/browser-storage-safety/SKILL.md): Decide where a web app keeps tokens and state by reasoning about the XSS blast radius of each store, not by convenience. Use when choosing how to persist session tokens, auth state, or any value an attacker on your origin would want to read.
- [bug-bounty](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/bug-bounty/SKILL.md): Hunt vulnerabilities in bug bounty programs effectively and within the rules: scope, methodology, safe proof, and reports that get accepted. Use when participating in a bug bounty or coordinated disclosure program.
- [clickjacking-defense](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/clickjacking-defense/SKILL.md): Stop UI redress attacks by declaring who may frame your pages, using frame-ancestors as the primary control and X-Frame-Options as the fallback. Use when hardening any page that performs sensitive actions on a click, especially authenticated dashboards and confirmation flows.
- [command-injection-defense](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/command-injection-defense/SKILL.md): Run external programs without ever building a shell string from untrusted input, using argument arrays that bypass the shell entirely. Use when a program shells out to another binary, especially with any value that came from a user, a file, or the network.
- [container-security](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/container-security/SKILL.md): Harden container images and runtime specs with minimal bases, non-root users, read-only filesystems, and dropped capabilities. Use when writing image or Kubernetes security settings or reviewing a container for privilege risk.
- [crypto-usage](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/crypto-usage/SKILL.md): Use cryptography by calling vetted libraries with authenticated defaults and storing keys in a KMS, never by designing a scheme. Use when adding encryption, choosing a cipher or mode, or reviewing code that handles keys or ciphertext.
- [csrf-defense](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/csrf-defense/SKILL.md): Block cross-site request forgery with SameSite cookies, per-session anti-CSRF tokens, and strict HTTP method discipline so a forged cross-origin request cannot act as the user. Use when building state-changing endpoints authenticated by cookies.
- [data-encryption](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/data-encryption/SKILL.md): Encrypt data at rest and in transit with vetted primitives and a managed key service that rotates on schedule. Use when handling sensitive data on disk or over the network, or when reviewing how a system stores and moves it.
- [dependency-auditing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/dependency-auditing/SKILL.md): Audit third-party packages by pinning resolved versions, scanning against advisory databases, and catching malicious lookalikes before install. Use when adding a dependency, wiring a vulnerability gate into CI, or reviewing what a project actually pulls in.
- [deserialization-safety](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/deserialization-safety/SKILL.md): Treat any serialized bytes from outside the program as hostile, parsing them through schema-validated formats instead of native object reconstructors. Use when reading pickles, Java or PHP serialized objects, YAML, or any encoded structure that arrives from a user, a queue, or a cache.
- [file-upload-safety](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/file-upload-safety/SKILL.md): Accept user file uploads without letting them become code execution, storage exhaustion, or a path into other users' data. Use when building an upload endpoint, an avatar or document feature, or any handler that writes client-supplied bytes to disk or object storage.
- [input-validation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/input-validation/SKILL.md): Validate untrusted input at every trust boundary with allowlists, canonicalization, and hard limits so malformed data never reaches logic. Use when accepting data from requests, files, uploads, or third-party APIs.
- [jwt-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/jwt-handling/SKILL.md): Use JSON Web Tokens safely by pinning the algorithm, keeping lifetimes short, and pairing them with a revocation path. Use when issuing or validating JWTs, designing a session scheme around them, or reviewing token-based auth.
- [least-privilege](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/least-privilege/SKILL.md): Scope every credential to the minimum actions it uses, with per-workload identities and expiry so a leak has a small blast radius. Use when writing an IAM policy, provisioning a service account, or reviewing an access grant.
- [mobile-app-security](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/mobile-app-security/SKILL.md): Protect a mobile app by storing secrets in the platform keystore, pinning certificates only where rotation is controlled, and treating obfuscation as delay rather than defense. Use when building or reviewing an iOS or Android app that holds tokens, keys, or user data on device.
- [oauth-flows](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/oauth-flows/SKILL.md): Implement OAuth 2.0 and OpenID Connect flows that bind the request end to end with PKCE, state, and exact redirect allowlists. Use when adding "sign in with" a provider, integrating a third-party API on a user's behalf, or reviewing an OAuth client.
- [open-redirect-defense](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/open-redirect-defense/SKILL.md): Validate every redirect destination against a server-side allowlist so a user-controlled target cannot bounce victims onto an attacker's site. Use when an endpoint reads a next, return_to, or callback parameter and sends the browser there.
- [password-storage](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/password-storage/SKILL.md): Store passwords with a slow, salted, memory-hard hash and a plan to raise the cost over time. Use when building signup or login, migrating off a weak hash, or reviewing how a system persists user passwords.
- [path-traversal-defense](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/path-traversal-defense/SKILL.md): Stop user-supplied path components from escaping the directory you meant to confine them to. Use when a filename, path segment, or archive entry from outside the program is joined into a filesystem path for reading, writing, or serving.
- [penetration-test-prep](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/penetration-test-prep/SKILL.md): Prepare for a penetration test by fixing scope, rules, and access up front, then turn its findings into tracked, verified remediation. Use when commissioning an external pentest or acting on the report one delivered.
- [phishing-resistance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/phishing-resistance/SKILL.md): Design authentication whose credentials cannot be relayed to a look-alike site, using origin-bound passkeys and hardware keys over phishable codes. Use when choosing MFA factors, building a passkey flow, or reviewing account recovery.
- [pii-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/pii-handling/SKILL.md): Minimize, classify, mask, and expire personal data so any leak or legal request reaches as little of it as possible. Use when designing storage, logging, or analytics that touch names, contacts, identifiers, or other personal data.
- [rate-limiting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/rate-limiting/SKILL.md): Limit requests by the cost they impose and the identity behind them, using token buckets, deliberate keys, and tiered responses to abuse. Use when protecting an API, a login flow, or any expensive endpoint from brute force, scraping, and accidental overload.
- [sast-integration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/sast-integration/SKILL.md): Wire a static analysis scanner into CI so it blocks real security bugs while staying under a defined noise budget. Use when adding a SAST tool to a pipeline or when an existing one is being ignored.
- [sbom-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/sbom-management/SKILL.md): Produce signed software bills of materials from real artifacts and consume them to answer "are we affected" fast. Use when setting up build output, responding to a new advisory, or fielding a customer SBOM request.
- [secrets-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/secrets-management/SKILL.md): Keep credentials out of source by loading them from a controlled store, scanning for leaks, and rotating on a schedule. Use when adding a secret to an app, cleaning one out of a repository, or setting up how a service reads credentials at runtime.
- [secrets-scanning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/secrets-scanning/SKILL.md): Scan commit history and CI for leaked credentials and rotate on every hit, because a pushed secret is already compromised. Use when hardening a repo against committed keys or responding to a suspected leak.
- [security-code-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/security-code-review/SKILL.md): Read a diff for security by tracing attacker-controlled input to dangerous operations and checking every trust boundary it crosses. Use when reviewing code that handles input, queries, files, output rendering, or authorization.
- [security-headers](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/security-headers/SKILL.md): Set the HTTP response headers that constrain what a browser will execute, embed, and leak on behalf of your origin. Use when hardening a web app against cross-site scripting, clickjacking, or referrer leakage, or when a security scan flags missing headers.
- [security-incident-response](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/security-incident-response/SKILL.md): Run a security breach through containment, evidence preservation, and notification duties in the right order, under time pressure, without destroying the record you will need. Use when you suspect or confirm a compromise: leaked credentials, unauthorized access, malware, or exfiltrated data.
- [security-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/security-review/SKILL.md): Review code for the vulnerabilities that actually get exploited, ranked by real risk with concrete attack scenarios. Use when reviewing changes that touch input handling, auth, secrets, files, queries, or network calls.
- [session-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/session-management/SKILL.md): Handle sessions so identifiers rotate on privilege change, expire on inactivity, can be revoked server-side, and ride only on hardened cookies. Use when issuing, storing, or validating session tokens after a user signs in.
- [sql-injection-defense](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/sql-injection-defense/SKILL.md): Eliminate SQL injection by sending data as bound parameters instead of concatenated query text, and auditing every raw-SQL escape hatch. Use when writing or reviewing code that builds database queries from variables.
- [ssrf-defense](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/ssrf-defense/SKILL.md): Prevent server-side request forgery by constraining where a user-influenced URL can make the server connect. Use when the server fetches a URL that came from a user: webhooks, link previews, image proxies, PDF renderers, or import-from-URL features.
- [supply-chain-defense](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/supply-chain-defense/SKILL.md): Harden the build pipeline by pinning what runs, generating provenance, and signing artifacts so tampering shows. Use when securing a CI/CD workflow, setting up artifact signing, or reviewing how releases are built and shipped.
- [threat-modeling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/threat-modeling/SKILL.md): Map assets, entry points, and STRIDE threats before writing code so defenses land in the design instead of a later patch. Use when starting a feature that handles auth, money, personal data, or external input.
- [tls-configuration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/tls-configuration/SKILL.md): Configure transport layer security with modern protocol versions, automated certificate renewal, and strict transport enforcement. Use when standing up HTTPS on a server, terminating TLS at a proxy, or hardening an endpoint that already serves traffic.
- [vulnerability-triage](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/vulnerability-triage/SKILL.md): Score incoming vulnerability reports the same way every time, tie each score to a fix deadline, and run disclosure on a predictable clock. Use when a vulnerability report arrives or when standing up a process to handle them.
- [xss-defense](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/xss-defense/SKILL.md): Prevent cross-site scripting by encoding output for its exact sink, keeping template autoescaping on, and backing it with a strict Content Security Policy. Use when rendering user-controlled data into HTML, attributes, JavaScript, or URLs.
- [zero-trust-basics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/security/zero-trust-basics/SKILL.md): Apply zero trust by authenticating and authorizing every request on its own merits and issuing only short-lived, narrowly scoped credentials. Use when designing service-to-service access, internal tooling, or any system that still trusts requests because of where they came from.
## Skills: spreadsheets
- [conditional-formatting](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/conditional-formatting/SKILL.md): Use formatting rules to surface exceptions and patterns automatically, without turning the sheet into a colour chart. Use when readers need to spot outliers or status at a glance.
- [data-validation-rules](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/data-validation-rules/SKILL.md): Constrain what can be entered into a spreadsheet so errors are prevented at input rather than found in analysis. Use when a spreadsheet is filled in by people.
- [excel-formulas](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/excel-formulas/SKILL.md): Write formulas that stay correct when rows are added and readable when someone else opens the file. Use when building any calculation in a spreadsheet.
- [financial-functions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/financial-functions/SKILL.md): Use present value, rate, and payment functions correctly, with consistent periods and sign conventions. Use when modelling loans, investments, or discounted cash flows.
- [lookup-functions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/lookup-functions/SKILL.md): Join data between sheets reliably using modern lookup functions, handling missing matches and duplicates explicitly. Use when combining data from more than one table.
- [pivot-tables](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/pivot-tables/SKILL.md): Summarise and cross-tabulate large tables quickly with pivots, keeping the source data clean and the refresh reliable. Use when aggregating data by category, period, or dimension.
- [power-query](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/power-query/SKILL.md): Build repeatable data transformations that refresh on demand, replacing manual cleaning steps with a recorded pipeline. Use when the same import and cleaning happens more than once.
- [spreadsheet-automation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/spreadsheet-automation/SKILL.md): Automate repetitive spreadsheet work with scripts, knowing when the task has outgrown a spreadsheet entirely. Use when the same manual steps are repeated on a schedule.
- [spreadsheet-charts](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/spreadsheet-charts/SKILL.md): Build charts that make the point clearly, choosing the type by the question and removing everything that does not carry meaning. Use when presenting spreadsheet data visually.
- [spreadsheet-collaboration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/spreadsheet-collaboration/SKILL.md): Share workbooks so several people can work without overwriting each other or creating competing versions. Use when more than one person edits the same spreadsheet.
- [spreadsheet-data-cleaning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/spreadsheet-data-cleaning/SKILL.md): Turn messy imported data into a clean flat table, fixing types, whitespace, duplicates, and inconsistent categories. Use before any analysis on data that came from elsewhere.
- [spreadsheet-performance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/spreadsheets/spreadsheet-performance/SKILL.md): Diagnose and fix slow spreadsheets by reducing volatile formulas, whole-column references, and unnecessary recalculation. Use when a workbook takes seconds to respond to an edit.
## Skills: sql
- [common-table-expressions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/common-table-expressions/SKILL.md): Use CTEs to name intermediate steps so a complex query reads as a sequence rather than a nest, and know when they cost performance. Use when a query has grown into nested subqueries nobody can follow.
- [deduplication-queries](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/deduplication-queries/SKILL.md): Find and remove duplicate rows deterministically, keeping the record you meant to keep. Use when a table has accumulated duplicates or an import needs a clean unique set.
- [null-semantics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/null-semantics/SKILL.md): Reason about SQL nulls in comparisons, aggregates, joins, and uniqueness so absent values stop producing wrong or missing rows. Use when a query silently drops rows or a NOT IN returns nothing.
- [pivot-and-unpivot](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/pivot-and-unpivot/SKILL.md): Reshape rows into columns and back, and know when the reshape belongs in SQL rather than in the reporting layer. Use when a report needs periods or categories as columns, or a wide table needs normalising.
- [query-readability](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/query-readability/SKILL.md): Write SQL other people can review, modify, and trust, with clear structure, meaningful aliases, and stated assumptions. Use when a query will be read again by anyone, including you.
- [recursive-queries](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/recursive-queries/SKILL.md): Walk hierarchies and graphs with recursive CTEs, with a termination condition and cycle protection so the query ends. Use when querying trees such as org charts, categories, threads, or dependency graphs.
- [sql-aggregation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/sql-aggregation/SKILL.md): Group and aggregate correctly, understanding what GROUP BY collapses, how HAVING differs from WHERE, and how nulls and empty groups behave. Use when producing counts, sums, and per-group summaries.
- [sql-date-time](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/sql-date-time/SKILL.md): Store, compare, and bucket timestamps with explicit time zones so reports do not drift by a day and ranges do not miss rows. Use when filtering by date, grouping by period, or storing an event time.
- [sql-joins](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/sql-joins/SKILL.md): Choose and write the right join so rows are neither lost nor multiplied, and know why a result set grew. Use when combining tables and the row count or the null columns look wrong.
- [sql-set-operations](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/sql-set-operations/SKILL.md): Combine result sets with UNION, INTERSECT, and EXCEPT, and know when a join or an exists clause is the better tool. Use when merging or comparing two query results rather than two tables.
- [upsert-patterns](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/upsert-patterns/SKILL.md): Insert or update in one statement without races or lost updates, using the engine's conflict handling rather than check-then-write. Use when writing records that may or may not already exist.
- [window-functions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/sql/window-functions/SKILL.md): Use window functions to rank, compare to neighbours, and compute running totals without collapsing rows or self-joining. Use when you need per-row context such as a rank, a previous value, or a running sum.
## Skills: systems-languages
- [c-memory-safety](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/c-memory-safety/SKILL.md): Write C with explicit ownership conventions, bounds discipline, and sanitizers wired into every test run. Use when writing or reviewing C code, or hunting memory corruption.
- [cpp-raii](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/cpp-raii/SKILL.md): Manage every resource through RAII with the rule of zero, correct smart-pointer selection, and move semantics. Use when writing modern C++ or reviewing code with manual new/delete or leaky error paths.
- [ffi-boundaries](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/ffi-boundaries/SKILL.md): Design foreign-function boundaries with explicit ownership, error translation, and contained panics/exceptions. Use when binding between Rust/Go/Python and C/C++ libraries or exposing your library over a C ABI.
- [go-concurrency](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/go-concurrency/SKILL.md): Structure goroutines with owned lifecycles, context propagation, and channel patterns that cannot leak or race. Use when writing concurrent Go or debugging goroutine leaks and data races.
- [go-project-layout](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/go-project-layout/SKILL.md): Organize Go packages by domain with internal boundaries, consumer-side interfaces, and structure that grows on demand. Use when starting a Go project or refactoring one into clearer packages.
- [rust-error-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/rust-error-handling/SKILL.md): Design Rust error types with the thiserror/anyhow split, context chains, and a deliberate panic policy. Use when structuring errors in Rust libraries and applications.
- [rust-ownership](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/rust-ownership/SKILL.md): Work with the borrow checker through ownership-first design instead of fighting it with clones and unsafe. Use when writing Rust or resolving borrow-checker errors that feel unwinnable.
- [systems-profiling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/systems-profiling/SKILL.md): Profile native code with perf and flamegraphs, then read cache, syscall, and allocation behavior to find the real bottleneck. Use when optimizing systems software or explaining why fast code is slow.
- [unsafe-code-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/unsafe-code-review/SKILL.md): Audit unsafe blocks by verifying documented invariants, minimizing surface, and testing under sanitizers and Miri. Use when reviewing unsafe Rust, C/C++ interop shims, or any code that bypasses language safety.
- [zero-cost-abstractions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/systems-languages/zero-cost-abstractions/SKILL.md): Verify that abstractions actually compile away by inspecting generated code and measuring, and know the costs that remain. Use when writing performance-critical Rust/C++ or judging whether an abstraction is free.
## Skills: testing
- [api-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/api-testing/SKILL.md): Test an HTTP API at its boundary so status codes, response schemas, error bodies, and auth paths all hold under real requests. Use when adding or reviewing tests for a service that other clients call over HTTP.
- [approval-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/approval-testing/SKILL.md): Assert hard-to-specify output by reviewing a human-readable snapshot once, approving it, then failing on any later diff. Use when the correct result is easy to recognize but tedious to write as explicit assertions.
- [assertion-libraries](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/assertion-libraries/SKILL.md): Pick an assertion style and write checks that fail with a message you can diagnose without a debugger. Use when test failures read as "expected true, got false" and you cannot tell what actually broke.
- [bdd-scenarios](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/bdd-scenarios/SKILL.md): Write given-when-then scenarios in domain language so stakeholders can read and confirm the behavior each test protects. Use when drafting acceptance criteria or Gherkin features for a user-facing rule.
- [browser-matrix](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/browser-matrix/SKILL.md): Choose which browsers, versions, and devices to test from real usage data instead of habit or a vendor's full grid. Use when cross-browser testing time or budget is finite and the matrix needs to reflect who actually visits.
- [chaos-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/chaos-testing/SKILL.md): Inject failures like killed instances and network latency on purpose to verify a system degrades gracefully instead of collapsing. Use when validating the resilience of a distributed system that claims to tolerate faults.
- [concurrency-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/concurrency-testing/SKILL.md): Force the thread interleavings that expose races by using barriers, stress loops, and linearizability checks instead of hoping the scheduler hits them. Use when testing locks, shared state, or lock-free code where a bug appears once in a thousand runs.
- [contract-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/contract-testing/SKILL.md): Verify a service boundary with a consumer-driven contract that records the payload the caller actually reads and that both sides check in CI. Use when two services deploy independently and an unannounced response change would silently break the consumer.
- [coverage-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/coverage-strategy/SKILL.md): Read coverage as a map of untested risk that steers the next test, rather than enforcing a percentage target. Use when deciding what to test next or when a team is tempted to mandate a coverage number.
- [database-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/database-testing/SKILL.md): Exercise data-access code, migrations, and transactions against the real database engine so constraints, rollbacks, and schema changes are proven rather than assumed. Use when tests for queries or migrations run on SQLite while production runs Postgres.
- [e2e-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/e2e-testing/SKILL.md): Write end-to-end tests that earn their cost by covering complete user journeys against stable selectors. Use when protecting a critical path like signup or checkout across the full stack.
- [exploratory-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/exploratory-testing/SKILL.md): Run structured unscripted testing with charters, tours, and timeboxed sessions to find bugs scripted tests never imagined. Use when probing a new or risky feature for problems no one thought to write a test for.
- [fuzz-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/fuzz-testing/SKILL.md): Fuzz a parser or protocol handler with a coverage-guided fuzzer, seed the corpus with real inputs, and triage crashes to unique root causes. Use when code consumes untrusted or complex bytes and hand-written cases cannot reach the states that break it.
- [golden-master](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/golden-master/SKILL.md): Capture the current output of untested legacy code as a recorded baseline so a refactor can prove it changed nothing. Use when about to restructure code whose behavior you must preserve but cannot yet specify.
- [integration-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/integration-testing/SKILL.md): Test the seams between modules with real dependencies where they are cheap and containerized ones where they are not. Use when verifying that components wired together honor the contracts unit tests assume in isolation.
- [load-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/load-testing/SKILL.md): Simulate realistic multi-user load with ramp profiles, think time, and pacing, then find where the system saturates. Use when validating capacity or headroom for a service before a launch or expected traffic spike.
- [mocking-time](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/mocking-time/SKILL.md): Control the clock in tests through an injectable time source so "now" is frozen and timezone behavior is explicit. Use when code reads the wall clock and a flaky or time-dependent test needs deterministic results.
- [mutation-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/mutation-testing/SKILL.md): Measure how strong a test suite is by mutating the code and checking the tests notice, exposing assertions that never actually fail. Use when coverage is high but you doubt the tests would catch a real regression.
- [pact-verification](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/pact-verification/SKILL.md): Verify a provider against its consumers' recorded pacts in CI so a breaking API change fails before it ships. Use when independently deployed services share an HTTP contract and you want to catch breaks without end-to-end staging.
- [performance-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/performance-testing/SKILL.md): Benchmark code so the numbers mean something: warm up, fix inputs, report variance, and gate regressions in CI. Use when measuring the speed of a function or comparing two implementations.
- [property-based-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/property-based-testing/SKILL.md): Generate many inputs to test invariants that must hold across a whole domain, and let shrinking reduce failures to a minimal case. Use when a rule should hold for all inputs, not just the few examples you would think to write.
- [regression-tests](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/regression-tests/SKILL.md): Pin every fixed bug with a test that fails before the fix and passes after, kept beside the code it guards. Use when closing a bug so the same defect cannot return silently through a later refactor or merge.
- [seed-data-management](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/seed-data-management/SKILL.md): Version and share seed datasets so they stay small, realistic, and reproducible across a team. Use when tests or local environments depend on fixture data that is drifting, ballooning, or diverging between developers.
- [smoke-tests](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/smoke-tests/SKILL.md): Define the short, stable suite of critical-path checks that runs after every deploy and blocks promotion the instant it fails. Use when a deploy has no fast gate and breakage is found by users instead of the pipeline.
- [snapshot-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/snapshot-testing/SKILL.md): Use snapshot tests for serialized output only, with disciplined review of every diff and hard limits on snapshot size. Use when pinning stable rendered output like markup or an API response shape.
- [tdd-rhythm](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/tdd-rhythm/SKILL.md): Run red-green-refactor honestly with the smallest failing test first, refusing test-after backfill dressed up as TDD. Use when building code with a clear behavioral spec and you want the tests to drive the design.
- [test-data-builders](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-data-builders/SKILL.md): Construct test objects through builders and factories with valid defaults so each test states only the fields it cares about. Use when shared fixture files couple unrelated tests and drift as the schema grows.
- [test-doubles](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-doubles/SKILL.md): Choose stubs, fakes, and mocks deliberately and default to verifying state over interaction so tests survive refactors. Use when a test needs to stand in for a slow, external, or nondeterministic dependency.
- [test-environment-parity](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-environment-parity/SKILL.md): Close the gaps between test and production by matching versions, data shape, and configuration paths so a passing suite actually predicts prod behavior. Use when tests are green but production breaks in ways staging never showed.
- [test-flakiness-budget](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-flakiness-budget/SKILL.md): Cap flaky tests with a measured budget, quarantine them off the merge gate, and burn them down under named owners and deadlines. Use when re-runs are how the team gets green and no one owns the flakes.
- [test-isolation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-isolation/SKILL.md): Make tests order-independent by resetting state, banning shared globals, and giving each worker its own resources. Use when tests pass in one order but fail when reordered, sharded, or run in parallel.
- [test-maintenance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-maintenance/SKILL.md): Refactor test code with the same care as production: extract helpers, remove duplication, and delete tests that no longer earn their place. Use when the test suite has become slow to change, repetitive, or full of tests nobody trusts.
- [test-naming](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-naming/SKILL.md): Name tests as full behavior sentences so the suite reads as a specification of what the system guarantees. Use when naming a new test or renaming vague tests like test1 or testWorks.
- [test-pyramid-audit](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-pyramid-audit/SKILL.md): Rebalance a top-heavy test suite toward fast unit tests without dropping the coverage the slow tests provide. Use when end-to-end tests dominate the suite and CI is slow, flaky, or expensive to run.
- [test-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-review/SKILL.md): Review tests with the same rigor as production code, checking that assertions truly constrain behavior, that error and edge cases exist, and that no safety was quietly deleted. Use when reviewing a pull request that adds, changes, or removes tests.
- [test-speed](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-speed/SKILL.md): Keep the suite fast enough to run on every change by measuring the slow tests, shaping the pyramid, cutting IO from the fast tier, and sharding. Use when the suite is slow enough that developers skip it or batch changes to avoid the wait.
- [test-tagging](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/test-tagging/SKILL.md): Tag tests by speed and scope so CI can run the right slice at the right time. Use when the suite is one undifferentiated blob and you need fast feedback on pull requests without dropping slow coverage.
- [testing-in-production](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/testing-in-production/SKILL.md): Verify changes against real traffic without risking users, using canaries, shadow traffic, and feature gates with automatic rollback. Use when a behavior cannot be trusted from staging alone and needs production load or data to prove out.
- [testing-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/testing-strategy/SKILL.md): Decide what to test, at which level, and what to skip, so tests catch real regressions without freezing the design. Use when writing tests or planning coverage for a change.
- [unit-test-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/unit-test-design/SKILL.md): Write unit tests that document behavior through explicit arrange-act-assert phases and a single assertion of intent. Use when writing or repairing a unit test that has grown hard to read.
- [visual-regression-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/testing/visual-regression-testing/SKILL.md): Catch unintended UI changes by diffing rendered screenshots against approved baselines with tuned thresholds and flake control. Use when protecting a component or page from visual drift across code changes.
## Skills: ui-ux
- [empty-and-error-states](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/empty-and-error-states/SKILL.md): Design the empty, loading, error, and edge states that most designs skip but users constantly hit. Use when designing any screen that can be empty, loading, or fail, which is nearly all of them.
- [information-architecture](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/information-architecture/SKILL.md): Organize a product's content and navigation around how users think, so they can find things and know where they are. Use when structuring an app's navigation, a site's sections, or a feature's information.
- [interaction-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/interaction-design/SKILL.md): Design how users act and the interface responds: affordances, feedback, states, and forgiving flows. Use when designing controls, flows, and interactive behavior, or fixing an interface that confuses or frustrates.
- [onboarding-ux](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/onboarding-ux/SKILL.md): Design a first-run experience that gets users to their first success fast, teaching by doing rather than by tour. Use when designing signup, first-run, or activation flows for a product.
- [usability-heuristics](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/usability-heuristics/SKILL.md): Evaluate and design interfaces against established usability heuristics to catch the common, predictable UX failures. Use when reviewing a UI for problems or designing one to avoid them.
- [usability-testing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/usability-testing/SKILL.md): Watch real users attempt real tasks to find where a design fails, with few participants and honest tasks. Use when validating a design or diagnosing why users struggle, before or after building.
- [user-flows](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/user-flows/SKILL.md): Map and design the paths a user takes to complete a goal, minimizing steps and dead ends. Use when designing a multi-step task, checkout, signup, or any flow, or diagnosing where users drop off.
- [ux-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/ux-writing/SKILL.md): Write the words inside an interface (labels, buttons, errors, empty states, microcopy) so they are clear, concise, and helpful. Use when writing or reviewing any text a user reads while using a product.
- [visual-hierarchy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/visual-hierarchy/SKILL.md): Guide the eye to what matters through size, contrast, spacing, and grouping so a screen reads at a glance. Use when a design feels cluttered, flat, or hard to scan, or when laying out any interface or page.
- [wireframing-prototyping](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ui-ux/wireframing-prototyping/SKILL.md): Use low- and high-fidelity wireframes and prototypes to test ideas cheaply before building. Use when exploring a design, aligning stakeholders, or validating a flow before committing engineering time.
## Skills: writing
- [audience-adaptation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/audience-adaptation/SKILL.md): Adapt what you write, how much, and how you frame it to the specific reader's knowledge, needs, and stakes. Use when the same content must reach different audiences, or when writing is missing its reader.
- [clear-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/clear-writing/SKILL.md): Write so the reader understands on the first pass: plain words, concrete nouns, one idea per sentence. Use when drafting or editing any prose that must be understood without effort.
- [concise-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/concise-writing/SKILL.md): Cut writing to its essential words so every one earns its place, without losing meaning or voice. Use when a piece is too long, dense, or padded, or whenever brevity respects the reader's time.
- [editing-and-revision](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/editing-and-revision/SKILL.md): Turn a rough draft into finished writing through structured revision passes: cut, clarify, then polish. Use when improving your own or others' writing after the first draft exists.
- [narrative-craft](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/narrative-craft/SKILL.md): Tell a story that holds attention and makes a point, through character, tension, and concrete scenes. Use when using storytelling in writing: an essay, a talk, a case study, a brand story, a personal account.
- [persuasive-writing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/persuasive-writing/SKILL.md): Make a case in writing that changes minds through a clear claim, real evidence, and honest handling of objections. Use when writing to convince: a proposal, a pitch, an argument, an opinion piece.
- [strong-openings](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/strong-openings/SKILL.md): Write openings that earn the next sentence: hook the reader, promise value, and get to the point fast. Use when a piece's beginning is slow, generic, or buries what matters.
- [structure-and-flow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/structure-and-flow/SKILL.md): Organize writing so the reader is carried from point to point without friction: logical order, transitions, and signposting. Use when a piece feels disorganized, jumpy, or hard to follow despite clear sentences.
- [voice-and-tone](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/voice-and-tone/SKILL.md): Develop a consistent writing voice and adjust tone to the context without sounding generic or robotic. Use when writing needs personality, a brand voice, or a register matched to the situation.
- [writing-with-evidence](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/writing/writing-with-evidence/SKILL.md): Support claims with specifics, data, and examples so writing is credible and concrete instead of vague assertion. Use when writing makes claims that need backing, or reads as generic and unconvincing.
## Prompts
- [ab-test-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/ab-test-plan.md): Design an experiment with the hypothesis, sample size, and decision rule fixed before it runs.
- [ad-copy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/ad-copy.md): Write advertising copy that leads with the benefit, speaks to one audience, and drives one clear action.
- [add-code-comments](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/add-code-comments.md): Add docstrings and comments that explain why, matching the code's existing style, without noise.
- [adjust-tone](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/adjust-tone.md): Rewrite text in a different tone (more formal, friendlier, more direct) while keeping the meaning.
- [agent-build-feature](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-build-feature.md): A strict brief that makes a coding agent implement a feature end to end, matching the codebase and verifying it works.
- [agent-complete-task](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-complete-task.md): A strict, goal-focused brief that makes a coding agent (Claude Code, Cursor, Antigravity) finish a task correctly and verify it.
- [agent-eval-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-eval-design.md): Design an evaluation for an AI agent or LLM feature: what to test, how to grade it, and how to catch regressions.
- [agent-explain-codebase](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-explain-codebase.md): A focused brief that makes a coding agent map an unfamiliar codebase so you (or it) can work in it confidently.
- [agent-fix-bug](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-fix-bug.md): A strict brief that makes a coding agent find the root cause of a bug, fix it minimally, and prove it is fixed.
- [agent-refactor-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-refactor-code.md): A strict brief that makes a coding agent refactor code without changing behavior, verifying nothing broke.
- [agent-system-prompt](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-system-prompt.md): Write a system prompt for an AI agent that defines its role, tools, boundaries, and output clearly enough to act reliably.
- [agent-task-breakdown](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-task-breakdown.md): Decompose a complex task into clear subtasks an AI agent (or agents) can execute and verify step by step.
- [agent-tool-definition](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-tool-definition.md): Write a tool/function definition for an AI agent with a description that steers use and parameters it fills correctly.
- [agent-workflow-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/agent-workflow-design.md): Design a multi-agent workflow with the right pattern, explicit handoffs, and human gates on consequential actions.
- [analyze-competitor-product](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/analyze-competitor-product.md): Analyse a competitor's product from public information, separating observation from inference.
- [analyze-performance](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/analyze-performance.md): Diagnose a performance problem from measurements rather than intuition, and propose the fix with the largest expected return.
- [api-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/api-design.md): Design a clean REST or GraphQL API from requirements, with sensible resources, methods, status codes, and error shapes.
- [api-docs-from-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/api-docs-from-code.md): Generate accurate reference documentation for an API from its code, marking every inference.
- [api-migration-guide](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/api-migration-guide.md): Write a guide that gets consumers from an old API version to a new one with every breaking change addressed.
- [apology-email](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/apology-email.md): Write a sincere, professional apology email that owns the mistake, addresses the impact, and offers a fix.
- [architecture-decision-record](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/architecture-decision-record.md): Write an ADR that captures a technical decision, its context, and its consequences so future teams know why.
- [assess-technical-debt](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/assess-technical-debt.md): Assess technical debt by what it costs now, and produce a paydown plan tied to upcoming work.
- [audit-accessibility](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/audit-accessibility.md): Audit a product against real assistive technology use, prioritised by who is blocked.
- [autoresearch](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/autoresearch.md): Run a full autonomous research investigation and return a verified, cited report: plan, search broadly, check primary sources, verify adversarially, and synthesize. Run like an /autoresearch command for a deep, trustworthy answer.
- [beta-program-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/beta-program-plan.md): Plan a beta with the right participants, defined success criteria, and a decision point at the end.
- [blog-outline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/blog-outline.md): Outline a blog post with a clear angle and a section flow before you write, so the draft comes easily.
- [brainstorm-divergent](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/brainstorm-divergent.md): Generate genuinely different ideas across the solution space, then converge on the strongest few.
- [brainstorm](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/brainstorm.md): Generate a range of ideas for anything quickly, from safe to bold, without self-censoring. A quick /brainstorm command.
- [break-down-task](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/break-down-task.md): Break a goal into an ordered, actionable plan with dependencies and a clear first step.
- [bug-bounty-report](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/bug-bounty-report.md): Write a clear bug bounty vulnerability report a triager can reproduce and rate fast, with steps, impact, and a fix.
- [bug-report-triage](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/bug-report-triage.md): Turn a vague bug report into a structured, actionable ticket with severity and next steps.
- [build-internal-tool](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/build-internal-tool.md): Specify an internal tool that removes real friction, with the simplest build that works.
- [build-spreadsheet-model](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/build-spreadsheet-model.md): Specify a spreadsheet model that is auditable, with inputs separated and checks built in.
- [build-website](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/build-website.md): Build a small site with the simplest stack that fits, fast by default and editable afterwards.
- [business-case](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/business-case.md): Make the case for an investment with costs, benefits, risks, and the option of not doing it.
- [business-model-canvas](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/business-model-canvas.md): Lay out how a business creates, delivers, and captures value, and check the pieces are consistent with each other.
- [campaign-brief](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/campaign-brief.md): Write a campaign brief with one audience, one message, one action, and a defined success measure.
- [career-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/career-plan.md): Build a career plan from a concrete target role, with the gaps named and evidence to be gathered.
- [case-study](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/case-study.md): Write a customer case study with the classic problem-solution-results arc and concrete, credible outcomes.
- [changelog-from-diff](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/changelog-from-diff.md): Turn a diff or commit list into user-facing changelog entries that describe outcomes, not code.
- [checklist-sop](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/checklist-sop.md): Turn a process into a clear checklist or standard operating procedure (SOP) anyone can follow without you.
- [churn-investigation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/churn-investigation.md): Investigate why customers are leaving, separating involuntary churn from genuine dissatisfaction.
- [cold-email](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/cold-email.md): Write a short, specific cold outreach email that respects the reader's time and gives a real reason to reply.
- [commit-message](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/commit-message.md): Write a clear conventional-commit message from a diff or a description of the change.
- [compare-options](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/compare-options.md): Compare options against criteria that matter and end with a defensible recommendation.
- [competitive-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/competitive-analysis.md): Compare competitors on what buyers actually weigh, using only public information.
- [content-calendar](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/content-calendar.md): Plan a content calendar from real audience questions, at a cadence that can be sustained.
- [content-outline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/content-outline.md): Outline an article, course, or long piece so the structure is sound before you write a word.
- [contract-review-checklist](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/contract-review-checklist.md): Extract the terms that matter from an agreement and flag deviations for a lawyer, without giving legal advice.
- [convert-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/convert-code.md): Translate code from one language or framework to another, idiomatic to the target, with the tricky parts flagged.
- [cost-optimization-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/cost-optimization-review.md): Review infrastructure and vendor spend for savings ranked by size, with the risk of each stated.
- [cost-reduction-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/cost-reduction-plan.md): Find genuine cost reduction ranked by size and risk, distinguishing waste from capability being cut.
- [course-outline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/course-outline.md): Outline a course sequenced so each lesson is learnable when it arrives, ending in a real capability.
- [cover-letter](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/cover-letter.md): Draft a specific, honest cover letter matching your experience to a role, without cliches.
- [critique](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/critique.md): Get honest, useful critical feedback on any piece of work, with strengths, weaknesses, and how to fix them. A quick /critique command.
- [customer-feedback-synthesis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/customer-feedback-synthesis.md): Turn scattered feedback into ranked themes with evidence, separating loud voices from representative ones.
- [customer-health-score](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/customer-health-score.md): Define a health score from behaviour that predicts churn, with thresholds that trigger action.
- [customer-interview-synthesis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/customer-interview-synthesis.md): Turn interview transcripts into findings with evidence, separating what people said from what they do.
- [customer-persona](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/customer-persona.md): Build a persona from evidence, capturing the job, the trigger, and the objection rather than demographics.
- [dashboard-spec](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/dashboard-spec.md): Specify a dashboard around the decisions it supports, with a small number of headline figures.
- [data-analysis-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/data-analysis-plan.md): Plan an analysis before touching the data, with the question, the method, and what would falsify the hypothesis.
- [data-quality-audit](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/data-quality-audit.md): Assess a dataset for the problems that would invalidate analysis, before anyone builds on it.
- [data-to-insights](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/data-to-insights.md): Read a table or dataset and report what it actually shows: findings, not decoration, with honest caveats.
- [database-schema](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/database-schema.md): Design a database schema from requirements with sensible tables, keys, relationships, indexes, and constraints.
- [debug-error](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/debug-error.md): Diagnose an error methodically from the message, code, and context, with the most likely cause first.
- [decision-brief](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/decision-brief.md): Frame a decision with real options, the trade-offs, a recommendation, and what would change it.
- [decision-matrix](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/decision-matrix.md): Build a weighted decision matrix to compare options against criteria and surface what the choice hinges on.
- [decline-politely](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/decline-politely.md): Say no clearly and kindly, to a request, invitation, or offer, without burning the relationship or over-explaining.
- [delegate-to-agents](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/delegate-to-agents.md): Decide which parts of a workflow to hand to agents and which must stay with a person, by reversibility.
- [design-api-integration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-api-integration.md): Design an integration with a third-party API so its failures and changes stay contained.
- [design-caching](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-caching.md): Design a caching layer with explicit invalidation, chosen for a specific access pattern rather than added generally.
- [design-data-model](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-data-model.md): Design a data model from access patterns and invariants, with the constraints that keep it correct.
- [design-diagram](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-diagram.md): Specify a technical diagram that answers one question at one level of abstraction.
- [design-doc](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-doc.md): Write an engineering design doc that states the problem, weighs options, and lets reviewers approve or push back.
- [design-experiment-program](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-experiment-program.md): Set up a programme of experiments with a prioritised hypothesis backlog and honest decision rules.
- [design-form](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-form.md): Design a form with the fewest fields that works, clear labels, and errors that help.
- [design-mcp-server](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-mcp-server.md): Design an MCP server with tools an agent selects correctly and boundaries that keep it safe.
- [design-notification-system](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-notification-system.md): Design notifications with a frequency budget, the right channel per message, and real user control.
- [design-observability](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-observability.md): Decide what to log, measure, and trace for a service so failures are diagnosable without adding noise.
- [design-pricing-experiment](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-pricing-experiment.md): Test a pricing change safely, given that pricing tests affect real revenue and existing customers.
- [design-slide-deck](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/design-slide-deck.md): Turn an argument into a deck with one idea per slide and headlines that carry the point.
- [devils-advocate](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/devils-advocate.md): Stress-test an idea, plan, or decision by arguing against it honestly, to find the flaws before reality does.
- [discovery-interview-guide](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/discovery-interview-guide.md): Write an interview guide that surfaces what people actually do rather than what they say they want.
- [dockerfile-generate](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/dockerfile-generate.md): Write a small, secure, cache-friendly Dockerfile for an application, with multi-stage builds and a non-root runtime.
- [elevator-pitch](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/elevator-pitch.md): Write a tight elevator pitch for a product, startup, or yourself that lands the value in 30 seconds.
- [eli-expert](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/eli-expert.md): Explain a topic at an expert level, assuming deep background and going straight to the substance.
- [email-professional](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/email-professional.md): Draft a professional email that gets to the point, lands the right tone, and makes the next step obvious.
- [escalation-policy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/escalation-policy.md): Define what gets escalated, to whom, and how fast, so problems reach the right person at the right time.
- [estimate-work](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/estimate-work.md): Estimate a task or project honestly, by decomposing it, surfacing unknowns, and giving a range not a false point.
- [excel-formula](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/excel-formula.md): Build or fix an Excel or Google Sheets formula from a plain-language description, explained and robust.
- [exec-one-pager](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/exec-one-pager.md): Write a one-page brief for executives that leads with the ask and the bottom line, backed by just enough evidence.
- [executive-summary](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/executive-summary.md): Compress a long document into a summary that stands alone and leads with the conclusion.
- [explain-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/explain-code.md): Explain what a piece of code does, why it is shaped that way, and where it can bite.
- [explain-like-im-five](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/explain-like-im-five.md): Explain any concept in genuinely simple terms with one honest analogy, without becoming wrong.
- [explain](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/explain.md): Explain anything clearly at the right level for the reader, from beginner to expert. A quick /explain command for any concept.
- [extract-action-items](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/extract-action-items.md): Pull every commitment, task, and deadline out of meeting notes or a thread, with owners.
- [faq-from-tickets](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/faq-from-tickets.md): Turn recurring support tickets into a FAQ that deflects them, using the customer's own phrasing.
- [faq-generator](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/faq-generator.md): Generate an FAQ from a product, doc, or topic, answering the questions people actually ask, concisely.
- [feature-prioritization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/feature-prioritization.md): Rank candidate work by value, effort, and confidence, with the reasoning visible enough to argue with.
- [feature-spec](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/feature-spec.md): Specify a feature with the problem, the behaviour, the edge cases, and what is out of scope.
- [financial-forecast](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/financial-forecast.md): Build a forecast from stated drivers rather than a growth percentage, with the assumptions exposed.
- [flashcards](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/flashcards.md): Turn notes or a topic into study flashcards that test recall of the things worth knowing, not trivia.
- [follow-up-email](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/follow-up-email.md): Write a polite, effective follow-up email that adds value and prompts a reply without nagging.
- [generate-pdf-document](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/generate-pdf-document.md): Specify a generated PDF that survives variable content, with fonts, page breaks, and accessibility handled.
- [git-help](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/git-help.md): Get the right git commands for a task or to safely undo a mistake, explained, with the destructive parts flagged.
- [goal](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/goal.md): Give an AI agent a goal and have it pursue it autonomously to completion, planning, executing, tracking, and verifying with minimal intervention. Run like a /goal command with a coding or task agent.
- [headline-hooks](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/headline-hooks.md): Generate strong headlines and hooks that earn attention honestly, in a range of angles to test.
- [hiring-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/hiring-plan.md): Plan hiring against real capacity gaps, with sequencing, cost, and ramp-up time included.
- [improve-prompt](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/improve-prompt.md): Rewrite a prompt to be clearer, more specific, and more likely to produce the intended result.
- [improve](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/improve.md): Make any piece of work better, keeping its intent and voice while fixing the weaknesses. A quick /improve command.
- [incident-response-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/incident-response-plan.md): Define how incidents are detected, classified, communicated, and closed, before the next one.
- [incident-status-update](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/incident-status-update.md): Write a calm, honest status update during an ongoing incident, sized for its audience.
- [interview-prep](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/interview-prep.md): Prepare for an interview by mapping your evidence to what the role actually requires.
- [interview-questions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/interview-questions.md): Generate interview questions that reveal real capability for a specific role, with what good answers sound like.
- [introduction-email](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/introduction-email.md): Write an introduction email, whether introducing yourself or connecting two other people, that is warm and useful.
- [investor-update](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/investor-update.md): Write a periodic investor update that leads with the numbers, states the asks, and does not bury bad news.
- [job-description](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/job-description.md): Write a clear, honest job description that attracts the right candidates and screens out the wrong ones.
- [knowledge-base-article](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/knowledge-base-article.md): Write a self-serve article that answers one question in the words customers actually use.
- [landing-page-copy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/landing-page-copy.md): Write landing page copy with a clear headline, benefit-led sections, proof, and one decisive call to action.
- [launch-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/launch-plan.md): Plan a launch with readiness checks, sequenced channels, and a defined follow-through after the spike.
- [learning-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/learning-plan.md): Build a realistic, practice-first plan to learn any skill, fitted to available time and a concrete goal.
- [linkedin-about](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/linkedin-about.md): Write a LinkedIn headline and About section that reads as a real person, leads with value, and invites the right connections.
- [linkedin-post](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/linkedin-post.md): Write a LinkedIn post that reads as a real professional story or insight, with a strong first line and a genuine takeaway.
- [literature-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/literature-review.md): Review a body of sources by synthesising across them rather than summarising each in turn.
- [market-sizing](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/market-sizing.md): Estimate a market from the bottom up, with assumptions visible enough to argue with.
- [meeting-agenda](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/meeting-agenda.md): Build a focused meeting agenda with clear objectives, timeboxed topics, and the decisions the meeting must produce.
- [meeting-minutes](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/meeting-minutes.md): Turn a transcript or rough notes into minutes people actually consult: decisions, actions, and open questions first.
- [meeting-request-email](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/meeting-request-email.md): Write an email requesting a meeting that states the purpose, respects their time, and makes scheduling easy.
- [mental-models](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/mental-models.md): Apply relevant mental models to a problem or decision to see it from angles you would otherwise miss.
- [metric-definition](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/metric-definition.md): Define a metric precisely enough that two people computing it independently get the same number.
- [multi-agent-workflow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/multi-agent-workflow.md): Design a multi-agent workflow: which agents, how they divide the work, how they hand off, and how to verify.
- [name-suggestions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/name-suggestions.md): Suggest clear, precise names for a variable, function, class, or feature, with tradeoffs.
- [negotiation-prep](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/negotiation-prep.md): Prepare for a negotiation with your goals, your walk-away, the other side's interests, and your best alternative.
- [networking-email](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/networking-email.md): Write a networking email that starts a genuine professional connection, leading with them and asking for little.
- [newsletter](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/newsletter.md): Write an email newsletter people actually open and read, with a hook subject, one clear theme, and real value.
- [objection-handling](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/objection-handling.md): Prepare honest answers to the objections a buyer will actually raise, including where the objection is correct.
- [okr-draft](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/okr-draft.md): Draft OKRs with an inspiring objective and measurable, outcome-based key results, avoiding vanity and task-lists.
- [onboard-new-hire](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/onboard-new-hire.md): Build a first-month plan that gets a new joiner to a real contribution in week one.
- [onboarding-flow](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/onboarding-flow.md): Design an onboarding flow that gets a user to first value quickly, cutting everything that delays it.
- [one-on-one-agenda](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/one-on-one-agenda.md): Prepare a one-to-one that belongs to the report, with space for what they need rather than a status update.
- [optimize-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/optimize-code.md): Make code faster or lighter by finding the real bottleneck first, with measured, behavior-preserving changes.
- [orchestrator-prompt](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/orchestrator-prompt.md): Write an orchestrator prompt that coordinates worker agents: delegating, tracking, and synthesizing their results.
- [outline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/outline.md): Turn a topic or goal into a clear structured outline before you write or build. A quick /outline command for any piece.
- [partnership-proposal](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/partnership-proposal.md): Propose a partnership stating what each side gains, with a small first step rather than a broad commitment.
- [performance-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/performance-review.md): Write a fair, specific performance review or peer feedback with concrete examples and actionable growth areas.
- [plan-localization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/plan-localization.md): Plan localisation covering extraction, translation workflow, and the layout and format issues that follow.
- [plan-migration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/plan-migration.md): Plan a migration between systems, versions, or providers with staged cutover and a rollback at every step.
- [plan-observability-rollout](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/plan-observability-rollout.md): Plan instrumentation across a system in stages, starting where blindness costs most.
- [plan-platform-migration](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/plan-platform-migration.md): Plan a move to a new platform or provider, with parallel running and a reversible cutover.
- [plan-rag-system](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/plan-rag-system.md): Plan a retrieval system with chunking, evaluation, and freshness decided before building.
- [plan-refactor](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/plan-refactor.md): Plan a refactor as a sequence of safe verified steps, with tests established before anything moves.
- [plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/plan.md): Turn a task or project into a clear, ordered plan with steps, milestones, and risks. A quick /plan command for anything you need to get done.
- [positioning-statement](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/positioning-statement.md): Write a positioning statement that names the audience, the alternative, and the one defensible difference.
- [postmortem-writeup](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/postmortem-writeup.md): Write a blameless incident postmortem that finds the systemic cause and produces real preventive actions.
- [pr-description](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/pr-description.md): Write a pull request description that helps reviewers: what changed, why, and how to verify, from a diff.
- [pre-mortem](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/pre-mortem.md): Run a pre-mortem: imagine the project already failed, work backward to the causes, and prevent them now.
- [press-release](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/press-release.md): Write a press release in standard format that leads with the news and reads like journalism, not a brochure.
- [prfaq](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/prfaq.md): Write an Amazon-style PR/FAQ (press release plus FAQ) to pressure-test a product idea by working backwards from the customer.
- [pricing-proposal](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/pricing-proposal.md): Propose a pricing structure with the value, margin, and competitive cases argued, and the migration cost stated.
- [prioritize-tasks](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/prioritize-tasks.md): Prioritize a task list by importance and urgency (Eisenhower matrix) and turn it into a clear order of action.
- [procurement-brief](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/procurement-brief.md): Write requirements for a purchase before looking at vendors, so the comparison is not shaped by whoever demos best.
- [product-description](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/product-description.md): Write a product description that sells the benefit, fits the channel, and stays honest about what the product is.
- [product-requirements-doc](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/product-requirements-doc.md): Write a product requirements document (PRD) that defines the problem, the users, and success, without prescribing the build.
- [product-strategy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/product-strategy.md): Set product direction by choosing who to serve and what not to build, with the bet stated explicitly.
- [promotion-packet](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/promotion-packet.md): Write a promotion packet or self-review that frames your work as impact at the next level, with evidence.
- [prompt-optimization](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/prompt-optimization.md): Improve an underperforming prompt through structured changes measured against fixed cases.
- [proofread](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/proofread.md): Fix grammar, spelling, and punctuation while preserving the author's voice and meaning.
- [pros-cons](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/pros-cons.md): Get a quick, honest pros and cons list for a decision or option to see the tradeoffs at a glance. A quick /pros-cons command.
- [qbr-outline](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/qbr-outline.md): Outline a quarterly business review that leads with outcomes and ends with decisions rather than activity.
- [quarterly-okr-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/quarterly-okr-review.md): Review objectives honestly against outcomes, separating execution failure from wrong strategy.
- [quarterly-planning](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/quarterly-planning.md): Turn objectives into a quarter of committed work that fits real capacity, with what is being dropped named.
- [readme-write](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/readme-write.md): Write a readme that lets a reader decide in a minute whether this is for them, then get it running.
- [refactor-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/refactor-code.md): Suggest refactorings that improve readability and structure without changing behavior, ranked by payoff.
- [reflect](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/reflect.md): Have an AI agent critique and improve its own work before delivering it, catching errors and gaps a first pass misses. Run like a /reflect command over a draft, plan, or answer.
- [regex-builder](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/regex-builder.md): Build a regular expression from a plain-language description, with an explanation and test cases.
- [release-announcement](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/release-announcement.md): Announce a release so users know what changed, what breaks, and what to do about it.
- [release-notes](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/release-notes.md): Write user-facing release notes from a changelog or list of changes, grouped and written for the reader.
- [reminder-email](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/reminder-email.md): Write a polite reminder email about a deadline, task, payment, or event that prompts action without nagging.
- [reply-to-email](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/reply-to-email.md): Draft a clear, appropriate reply to an email that addresses what was asked and moves it forward.
- [repurpose-content](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/repurpose-content.md): Turn one piece of content into formats for other channels, adapted to each rather than copy-pasted.
- [request-email](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/request-email.md): Write an email that asks for something (a favor, information, approval, help) clearly and in a way that gets a yes.
- [research-brief](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/research-brief.md): Scope a research question so the work is bounded, the sources are named, and the output is decided in advance.
- [resume-bullets](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/resume-bullets.md): Turn your work into strong resume bullet points with action verbs and quantified impact, honestly.
- [resume-summary](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/resume-summary.md): Write a resume summary or professional profile that positions you for a specific role in three or four strong lines.
- [review-accessibility](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/review-accessibility.md): Review an interface for accessibility barriers, prioritised by who is blocked rather than by rule count.
- [review-data-privacy](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/review-data-privacy.md): Review a feature for privacy: what is collected, where it goes, how long it stays, and whether deletion works.
- [review-dependencies](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/review-dependencies.md): Assess a project's dependencies for risk, maintenance burden, and whether each still earns its place.
- [review-infrastructure](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/review-infrastructure.md): Review infrastructure configuration for reliability, cost, and security problems before they reach production.
- [review-my-code](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/review-my-code.md): Review code for bugs, security issues, and clarity, with severity-ranked findings and concrete fixes.
- [review-security](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/review-security.md): Review code or a design for security weaknesses, ranked by real exploitability rather than by checklist coverage.
- [rewrite-for-clarity](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/rewrite-for-clarity.md): Rewrite any text to be clearer and shorter without changing its meaning or losing content.
- [rfc-proposal](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/rfc-proposal.md): Write a technical RFC (request for comments) that proposes a change and invites the team to challenge it.
- [risk-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/risk-analysis.md): Surface what can go wrong with a plan, ranked by expected damage, with mitigations that change the odds.
- [roadmap-draft](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/roadmap-draft.md): Draft a roadmap communicating direction and confidence, without implying dates the team cannot hold.
- [root-cause-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/root-cause-analysis.md): Find the real root cause of a problem with the 5 Whys, getting past symptoms to the systemic fix.
- [run-company-standup](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/run-company-standup.md): Produce a daily operating brief across every function, ranked by what needs a decision today.
- [sales-outreach-sequence](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/sales-outreach-sequence.md): Draft a multi-step outreach sequence grounded in research about the recipient, for a human to review and send.
- [second-order-thinking](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/second-order-thinking.md): Think through the downstream consequences of a decision, past the obvious first effect to what it causes next.
- [security-incident-response](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/security-incident-response.md): Respond to a suspected security incident with containment, evidence preservation, and the right escalation.
- [seo-article](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/seo-article.md): Write an SEO article that genuinely answers the search intent, structured for readers and search engines both.
- [seo-content-brief](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/seo-content-brief.md): Brief a piece of content that serves the searcher's intent first and search engines second.
- [shell-command](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/shell-command.md): Get the right terminal command for a task, explained, with the dangerous parts flagged before you run it.
- [skill-gap-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/skill-gap-analysis.md): Assess the gap between current and required capability using demonstrated evidence rather than confidence.
- [social-media-post](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/social-media-post.md): Write a social media post or caption tuned to the platform, with a hook, a point, and a clear call to action.
- [socratic-tutor](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/socratic-tutor.md): Teach a topic by asking questions that lead the learner to build the understanding themselves.
- [sql-from-question](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/sql-from-question.md): Translate a plain-language question into correct SQL against a given schema, stating every assumption.
- [stakeholder-map](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/stakeholder-map.md): Identify who is affected by a decision, what each needs, and how they should be engaged.
- [standup-summary](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/standup-summary.md): Turn work notes, commits, or a task list into a crisp standup update that surfaces blockers first.
- [steps](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/steps.md): Get clear step-by-step instructions for how to do something, in order, that anyone can follow. A quick /steps command.
- [story-narrative](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/story-narrative.md): Turn a message, brand, or experience into a story with a real arc that makes the point land and stick.
- [style-guide](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/style-guide.md): Write a style guide specific enough to settle real disagreements rather than restating general advice.
- [summarize-document](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/summarize-document.md): Summarize any document into a faithful, layered brief that never invents content.
- [summarize](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/summarize.md): Summarize anything (text, article, thread, transcript, notes) into the key points, fast. A quick /summarize command for any content.
- [support-macro-set](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/support-macro-set.md): Write reusable support replies that explain clearly while leaving the specifics to be personalised.
- [survey-questions](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/survey-questions.md): Write survey or research questions that get honest, useful data without leading, loading, or confusing respondents.
- [swot-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/swot-analysis.md): Run a SWOT analysis (strengths, weaknesses, opportunities, threats) that is specific and leads to actions.
- [system-design-answer](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/system-design-answer.md): Answer a system design question the way a strong senior engineer would, from requirements to tradeoffs to scale.
- [technical-due-diligence](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/technical-due-diligence.md): Assess a codebase and its engineering practice for risk, from what can be observed.
- [technical-tutorial](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/technical-tutorial.md): Write a tutorial that gets a reader to a working result, with every step tested and nothing assumed.
- [test-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/test-plan.md): Write a test plan for a feature or release: what to test, the scenarios and edge cases, and the risk-based priorities.
- [thank-you-note](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/thank-you-note.md): Write a genuine thank-you note that is specific about what you appreciated, not generic gratitude.
- [tldr](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/tldr.md): Get the one-line or few-bullet bottom line of anything long, instantly. A quick /tldr command for when you just need the gist.
- [translate-text](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/translate-text.md): Translate text naturally into a target language, preserving tone, register, and meaning.
- [triage-inbox](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/triage-inbox.md): Sort a backlog of incoming items by what actually needs action, with everything else disposed of.
- [troubleshooting-guide](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/troubleshooting-guide.md): Write a guide organised by the symptom a user sees, leading to the cause and the fix.
- [tweet-thread](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/tweet-thread.md): Write an X/Twitter thread with a scroll-stopping first post, one idea per post, and a payoff that earns the read.
- [unit-economics-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/unit-economics-analysis.md): Work out whether one customer or transaction makes money, with every variable cost included.
- [usability-test-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/usability-test-plan.md): Plan a usability test with realistic tasks and observation rather than opinion gathering.
- [user-story-breakdown](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/user-story-breakdown.md): Break a feature idea into small, testable user stories with acceptance criteria and honest unknowns.
- [vendor-evaluation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/vendor-evaluation.md): Compare vendors against weighted criteria fixed before the vendor list, including total and exit cost.
- [video-description](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/video-description.md): Write a YouTube video description that hooks the reader, helps search, and includes the standard useful sections.
- [weekly-plan](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/weekly-plan.md): Turn a pile of tasks and goals into a realistic weekly plan focused on what actually matters.
- [weekly-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/weekly-review.md): Review the week honestly against what was planned, and set the next one from what you learned.
- [win-loss-analysis](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/win-loss-analysis.md): Analyse why deals were won and lost from evidence, separating stated reasons from real ones.
- [workshop-design](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/workshop-design.md): Design a workshop where participants do the work rather than watch a presentation.
- [write-agents-md](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-agents-md.md): Write the repository instruction file that coding agents read, covering conventions they cannot infer.
- [write-blog-post](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-blog-post.md): Write a blog post with a clear angle, a scannable structure, and a real takeaway, in your voice not generic filler.
- [write-chaos-experiment](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-chaos-experiment.md): Design a failure injection experiment that tests a specific resilience hypothesis safely.
- [write-documentation](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-documentation.md): Write clear documentation for code, an API, or a feature, structured for the reader who needs to use it.
- [write-error-messages](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-error-messages.md): Rewrite error messages so the reader knows what happened, why, and what to do next.
- [write-eval-suite](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-eval-suite.md): Build an evaluation suite for an AI feature with cases, criteria, and thresholds fixed in advance.
- [write-integration-test](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-integration-test.md): Write integration tests that exercise real boundaries and fail for real reasons rather than mirroring the implementation.
- [write-load-test](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-load-test.md): Design a load test that answers a specific capacity question rather than generating traffic for its own sake.
- [write-postmortem](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-postmortem.md): Write a blameless postmortem that finds systemic causes and produces owned actions.
- [write-proposal](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-proposal.md): Write a client proposal that shows you understood the problem, with scope, price, and risks stated.
- [write-report](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-report.md): Write a report that leads with the finding, supports it proportionally, and states its own limits.
- [write-runbook](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-runbook.md): Write an operational runbook someone can follow at 3am without prior knowledge of the system.
- [write-technical-spec](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-technical-spec.md): Write a technical design document with the problem, the approach, the alternatives, and the risks.
- [write-tests](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/write-tests.md): Generate meaningful tests for given code, edge cases first, in the project's own style.
- [youtube-script](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/prompts/youtube-script.md): Write a YouTube video script with a strong hook, a clear structure, and retention built in, in your voice.