byerlikaya/claude-starter-kit

byerlikaya/claude-starter-kit · claude-starter/CLAUDE.md

byerlikaya/claude-starter-kit · claude-starter/skills/a11y/SKILL.md · Frontend accessibility audit (WCAG): semantic HTML, keyboard access, focus management, contrast, ARIA, screen…

byerlikaya/claude-starter-kit · claude-starter/skills/adr/SKILL.md · Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under…

byerlikaya/claude-starter-kit · claude-starter/skills/api-design/SKILL.md · API contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A…

byerlikaya/claude-starter-kit · claude-starter/skills/automode-policy/SKILL.md · Auto-mode classifier config: inspect what the classifier that now answers permission prompts is configured with, and…

byerlikaya/claude-starter-kit · claude-starter/skills/brainstorm/SKILL.md · Divergent discovery BEFORE planning: turn a fuzzy ask into 2–4 scoped options + named unknowns, pick a direction, hand…

byerlikaya/claude-starter-kit · claude-starter/skills/ci-pipeline/SKILL.md · CI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.

byerlikaya/claude-starter-kit · claude-starter/skills/code-review-csk/SKILL.md · Code review discipline: severity-ranked, reasoned feedback on whether a change improves the system's overall code…

byerlikaya/claude-starter-kit · claude-starter/skills/commit-message/SKILL.md · Conventional Commits: reads the staged diff and proposes `type(scope): summary`, with body/footer when needed. One…

byerlikaya/claude-starter-kit · claude-starter/skills/confidence-check/SKILL.md · Readiness gate BEFORE writing implementation code: does this already exist, does it fit the project's architecture, is…

byerlikaya/claude-starter-kit · claude-starter/skills/cqrs-aop-module/SKILL.md · Default .NET backend pattern: MediatR CQRS handler/command/query, IResult/IDataResult, Autofac AOP…

byerlikaya/claude-starter-kit · claude-starter/skills/db-migration/SKILL.md · Apply schema migrations safely: detect the tool, classify the change by risk, gate destructive ones behind approval…

byerlikaya/claude-starter-kit · claude-starter/skills/dependency-audit/SKILL.md · Dependency risk assessment, read-only: known CVEs, deprecated packages, licence compliance, maintenance status…

byerlikaya/claude-starter-kit · claude-starter/skills/dependency-upgrade/SKILL.md · Bring dependencies current without breaking the build: find what is vulnerable, deprecated or behind, classify each…

byerlikaya/claude-starter-kit · claude-starter/skills/deploy/SKILL.md · Ship a build reversibly — to a host you manage or a platform that manages it. Pick the topology first, keep the…

byerlikaya/claude-starter-kit · claude-starter/skills/docs-writer/SKILL.md · Keeps documentation in sync with the code: README, usage and related docs when a public API or behavior changes. Leaves…

byerlikaya/claude-starter-kit · claude-starter/skills/eval-grader/SKILL.md · Measure output quality, don't vibe it: score a generative task with a two-layer grader — deterministic code metrics +…

byerlikaya/claude-starter-kit · claude-starter/skills/frontend-design/SKILL.md · Visual and UX design quality for interfaces: hierarchy, spacing rhythm, typographic scale, a restrained color system…

byerlikaya/claude-starter-kit · claude-starter/skills/frontend-rn-expo/SKILL.md · OPTIONAL, stack-specific: React Native + Expo (prebuild). Mobile RN projects only; the generic principles live in the…

byerlikaya/claude-starter-kit · claude-starter/skills/frontend/SKILL.md · Stack-agnostic frontend discipline (web · mobile · desktop): component structure, state, data…

byerlikaya/claude-starter-kit · claude-starter/skills/handoff/SKILL.md · Session handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to…

byerlikaya/claude-starter-kit · claude-starter/skills/i18n-integrity/SKILL.md · Translation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals…

byerlikaya/claude-starter-kit · claude-starter/skills/incident-runbook/SKILL.md · Production incident response: diagnose → mitigate → resolve, then a blameless postmortem and a repeatable runbook. Stop…

byerlikaya/claude-starter-kit · claude-starter/skills/iterate/SKILL.md · Refine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.

byerlikaya/claude-starter-kit · claude-starter/skills/mcp-builder/SKILL.md · Build a Model Context Protocol (MCP) server so an AI client can call your tools/resources: design tool schemas, pick a…

byerlikaya/claude-starter-kit · claude-starter/skills/observability/SKILL.md · Stack-agnostic observability: structured logs, correlation ids, metrics and traces; no PII or secrets in logs. Makes a…

byerlikaya/claude-starter-kit · claude-starter/skills/performance/SKILL.md · Stack-agnostic performance: measure first, find the bottleneck, then optimise. N+1, needless allocation, wrong async…

byerlikaya/claude-starter-kit · claude-starter/skills/privacy-compliance/SKILL.md · KVKK/GDPR audit method: data inventory, purpose/basis/retention, minimisation, consent, transparency, data-subject…

byerlikaya/claude-starter-kit · claude-starter/skills/red-team/SKILL.md · Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted…

byerlikaya/claude-starter-kit · claude-starter/skills/reflect/SKILL.md · Retrospective self-audit after nontrivial work: unverified assumptions, skipped items, is-this-the-right- approach —…

byerlikaya/claude-starter-kit · claude-starter/skills/release/SKILL.md · Versioning and CHANGELOG: SemVer mapped from Conventional Commits, Keep a Changelog format, tagging, pre-release…

byerlikaya/claude-starter-kit · claude-starter/skills/security-scan/SKILL.md · Stack-agnostic security audit: map the attack surface, trace untrusted input to dangerous calls, surface dependency and…

byerlikaya/claude-starter-kit · claude-starter/skills/sonarqube-check/SKILL.md · SonarQube quality gate, any language, no company server needed: run SonarQube Community Build locally (Docker), read…

byerlikaya/claude-starter-kit · claude-starter/skills/spec-planning/SKILL.md · Spec-first planning: task breakdown, measurable acceptance criteria, dependency order, risk priority. planner-csk…

byerlikaya/claude-starter-kit · claude-starter/skills/systematic-debugging/SKILL.md · Root-cause a bug before touching a fix: reproduce, isolate, form and test a hypothesis, confirm the cause, then fix and…

byerlikaya/claude-starter-kit · claude-starter/skills/teamboard/SKILL.md · Shared team board: claim a work item before starting, hand it over, finish it. The claim is a git-ref lock, so two…

byerlikaya/claude-starter-kit · claude-starter/skills/testing/SKILL.md · The how of testing: pyramid, AAA, isolation, risk coverage, determinism. Guarantees the DoD's "tests are green"…

byerlikaya/claude-starter-kit · claude-starter/skills/threat-model/SKILL.md · Scope a security audit BEFORE scanning, to cut false positives: map assets, entry points, trust boundaries and 5-8…

byerlikaya/claude-starter-kit · claude-starter/skills/token-budget/SKILL.md · Context/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.

byerlikaya/claude-starter-kit · claude-starter/skills/trace-scan/SKILL.md · Trace scan (§4.1/§4.2): before a commit, scans the staged changes and the message for AI traces (co-author trailers…

byerlikaya/claude-starter-kit · claude-starter/skills/worktree/SKILL.md · Isolate risky or parallel file-mutating work in a git worktree so the main tree's uncommitted changes are…

byerlikaya/claude-starter-kit · plugin/skills/a11y/SKILL.md · Frontend accessibility audit (WCAG): semantic HTML, keyboard access, focus management, contrast, ARIA, screen…

byerlikaya/claude-starter-kit · plugin/skills/adr/SKILL.md · Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under…

byerlikaya/claude-starter-kit · plugin/skills/api-design/SKILL.md · API contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A…

byerlikaya/claude-starter-kit · plugin/skills/automode-policy/SKILL.md · Auto-mode classifier config: inspect what the classifier that now answers permission prompts is configured with, and…

byerlikaya/claude-starter-kit · plugin/skills/brainstorm/SKILL.md · Divergent discovery BEFORE planning: turn a fuzzy ask into 2–4 scoped options + named unknowns, pick a direction, hand…

byerlikaya/claude-starter-kit · plugin/skills/ci-pipeline/SKILL.md · CI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.

byerlikaya/claude-starter-kit · plugin/skills/code-review-csk/SKILL.md · Code review discipline: severity-ranked, reasoned feedback on whether a change improves the system's overall code…

byerlikaya/claude-starter-kit · plugin/skills/commit-message/SKILL.md · Conventional Commits: reads the staged diff and proposes `type(scope): summary`, with body/footer when needed. One…

byerlikaya/claude-starter-kit · plugin/skills/confidence-check/SKILL.md · Readiness gate BEFORE writing implementation code: does this already exist, does it fit the project's architecture, is…

byerlikaya/claude-starter-kit · plugin/skills/cqrs-aop-module/SKILL.md · Default .NET backend pattern: MediatR CQRS handler/command/query, IResult/IDataResult, Autofac AOP…

byerlikaya/claude-starter-kit · plugin/skills/db-migration/SKILL.md · Apply schema migrations safely: detect the tool, classify the change by risk, gate destructive ones behind approval…

byerlikaya/claude-starter-kit · plugin/skills/dependency-audit/SKILL.md · Dependency risk assessment, read-only: known CVEs, deprecated packages, licence compliance, maintenance status…

byerlikaya/claude-starter-kit · plugin/skills/dependency-upgrade/SKILL.md · Bring dependencies current without breaking the build: find what is vulnerable, deprecated or behind, classify each…

byerlikaya/claude-starter-kit · plugin/skills/deploy/SKILL.md · Ship a build reversibly — to a host you manage or a platform that manages it. Pick the topology first, keep the…

byerlikaya/claude-starter-kit · plugin/skills/docs-writer/SKILL.md · Keeps documentation in sync with the code: README, usage and related docs when a public API or behavior changes. Leaves…

byerlikaya/claude-starter-kit · plugin/skills/eval-grader/SKILL.md · Measure output quality, don't vibe it: score a generative task with a two-layer grader — deterministic code metrics +…

byerlikaya/claude-starter-kit · plugin/skills/frontend-design/SKILL.md · Visual and UX design quality for interfaces: hierarchy, spacing rhythm, typographic scale, a restrained color system…

byerlikaya/claude-starter-kit · plugin/skills/frontend-rn-expo/SKILL.md · OPTIONAL, stack-specific: React Native + Expo (prebuild). Mobile RN projects only; the generic principles live in the…

byerlikaya/claude-starter-kit · plugin/skills/frontend/SKILL.md · Stack-agnostic frontend discipline (web · mobile · desktop): component structure, state, data…

byerlikaya/claude-starter-kit · plugin/skills/handoff/SKILL.md · Session handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to…

byerlikaya/claude-starter-kit · plugin/skills/i18n-integrity/SKILL.md · Translation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals…

byerlikaya/claude-starter-kit · plugin/skills/incident-runbook/SKILL.md · Production incident response: diagnose → mitigate → resolve, then a blameless postmortem and a repeatable runbook. Stop…

byerlikaya/claude-starter-kit · plugin/skills/iterate/SKILL.md · Refine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.

byerlikaya/claude-starter-kit · plugin/skills/mcp-builder/SKILL.md · Build a Model Context Protocol (MCP) server so an AI client can call your tools/resources: design tool schemas, pick a…

byerlikaya/claude-starter-kit · plugin/skills/observability/SKILL.md · Stack-agnostic observability: structured logs, correlation ids, metrics and traces; no PII or secrets in logs. Makes a…

byerlikaya/claude-starter-kit · plugin/skills/performance/SKILL.md · Stack-agnostic performance: measure first, find the bottleneck, then optimise. N+1, needless allocation, wrong async…

byerlikaya/claude-starter-kit · plugin/skills/privacy-compliance/SKILL.md · KVKK/GDPR audit method: data inventory, purpose/basis/retention, minimisation, consent, transparency, data-subject…

byerlikaya/claude-starter-kit · plugin/skills/red-team/SKILL.md · Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted…

byerlikaya/claude-starter-kit · plugin/skills/reflect/SKILL.md · Retrospective self-audit after nontrivial work: unverified assumptions, skipped items, is-this-the-right- approach —…

byerlikaya/claude-starter-kit · plugin/skills/release/SKILL.md · Versioning and CHANGELOG: SemVer mapped from Conventional Commits, Keep a Changelog format, tagging, pre-release…

byerlikaya/claude-starter-kit · plugin/skills/security-scan/SKILL.md · Stack-agnostic security audit: map the attack surface, trace untrusted input to dangerous calls, surface dependency and…

byerlikaya/claude-starter-kit · plugin/skills/sonarqube-check/SKILL.md · SonarQube quality gate, any language, no company server needed: run SonarQube Community Build locally (Docker), read…

byerlikaya/claude-starter-kit · plugin/skills/spec-planning/SKILL.md · Spec-first planning: task breakdown, measurable acceptance criteria, dependency order, risk priority. planner-csk…

byerlikaya/claude-starter-kit · plugin/skills/systematic-debugging/SKILL.md · Root-cause a bug before touching a fix: reproduce, isolate, form and test a hypothesis, confirm the cause, then fix and…

byerlikaya/claude-starter-kit · plugin/skills/teamboard/SKILL.md · Shared team board: claim a work item before starting, hand it over, finish it. The claim is a git-ref lock, so two…

byerlikaya/claude-starter-kit · plugin/skills/testing/SKILL.md · The how of testing: pyramid, AAA, isolation, risk coverage, determinism. Guarantees the DoD's "tests are green"…

byerlikaya/claude-starter-kit · plugin/skills/threat-model/SKILL.md · Scope a security audit BEFORE scanning, to cut false positives: map assets, entry points, trust boundaries and 5-8…

byerlikaya/claude-starter-kit · plugin/skills/token-budget/SKILL.md · Context/token discipline: subagent isolation, output = summary, move-to-file, delegation threshold, lean skills.

byerlikaya/claude-starter-kit · plugin/skills/trace-scan/SKILL.md · Trace scan (§4.1/§4.2): before a commit, scans the staged changes and the message for AI traces (co-author trailers…

byerlikaya/claude-starter-kit · plugin/skills/worktree/SKILL.md · Isolate risky or parallel file-mutating work in a git worktree so the main tree's uncommitted changes are…