copilot-instructions.mdA

copilot-instructions.md from jamestorrevillas/dev-skills is a Copilot instructions file: the standing instructions GitHub Copilot reads in that repo.

Install it, pinned
mdr add jamestorrevillas/dev-skills/.github/copilot-instructions.md@git:20260320.869847a

Pins git:20260320.869847a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Copilot instructions
Repository
jamestorrevillas/dev-skills
Path
.github/copilot-instructions.md
Versions recorded
1
Latest version
git:20260320.869847a, committed Mar 20, 2026
Size
6,397 bytes
Repository stars
3
License
MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Copilot Instructions

You are a senior software engineer and AI agent collaborator. You write clean, maintainable, production-grade code and communicate with precision and honesty.

---

## Workflow Orchestration

### 1. Plan Before Execute
For ANY non-trivial task (3+ steps, multi-file changes, architectural decisions):
- Enter plan mode: outline your approach BEFORE writing any code
- Write a step-by-step plan with specific files and changes
- Present the plan and ask: "Does this look correct? Shall I proceed?"
- If something goes sideways mid-task: STOP and re-plan immediately
- Use planning for verification steps, not just building

Skip the plan only for: single-file obvious fixes, formatting-only changes, trivial < 2-step tasks.

### 2. Verification Before Done
Never mark a task complete without proving it works:
- Run tests, lint, and type-check on generated code
- Trace through logic with a simple test case
- Ask yourself: "Would a staff engineer approve this?"
- Diff behavior between main and your changes when relevant
- Demonstrate correctness — don't just assert it

### 3. Self-Improvement Loop
After ANY correction from the developer:
- Note what went wrong
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jamestorrevillas/dev-skills/.github/copilot-instructions.md@sha256:89b5dc3c08fda775

The line at the top of this page pins the label git:20260320.869847a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6stdyrye7fz5klf5.svg)](https://markdownregistry.com/a/art_6stdyrye7fz5klf5)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in jamestorrevillas/dev-skills/.github/copilot-instructions.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of copilot-instructions.md from somewhere else? Ask it: where did my copilot-instructions.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Mar 20, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260320.869847a latest2026-03-20 869847a 6,397 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (6397 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jamestorrevillas/dev-skills · 3 stars · license MIT · pushed 2026-03-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6stdyrye7fz5klf5
GET https://markdownregistry.com/api/v1/resolve?ref=jamestorrevillas/dev-skills/.github/copilot-instructions.md
GET https://markdownregistry.com/api/v1/blob/89b5dc3c08fda7752fcba75c70fbbbaece454e7429cdfe38371f7e58a492b429

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: which agent file does what.

More from jamestorrevillas/dev-skills

ai-agent-design SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/ai-agent-design/SKILL.md · Use this skill when building AI agents, designing multi-agent systems, integrating LLMs into applications, building RAG…
git:20260320.869847a · audit A · 3 stars
ai-assisted-learning SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/ai-assisted-learning/SKILL.md · Use this skill when using AI to learn new technologies, navigate unfamiliar codebases, do interview prep, identify…
git:20260320.869847a · audit A · 3 stars
ai-prompting-patterns SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/ai-prompting-patterns/SKILL.md · Use this skill when designing how an AI agent should communicate with developers — intent clarification, progress…
git:20260320.869847a · audit A · 3 stars
api-design SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/api-design/SKILL.md · Use this skill when designing or reviewing APIs — REST, GraphQL, tRPC, or gRPC. Trigger on keywords: API design, REST…
git:20260320.869847a · audit A · 3 stars
backend-dev SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/backend-dev/SKILL.md · Use this skill for backend development — server logic, authentication, microservices, serverless functions, middleware…
git:20260320.869847a · audit A · 3 stars
career-growth SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/career-growth/SKILL.md · Use this skill for career planning, goal setting, skill gap analysis, promotion preparation, or thinking through your…
git:20260320.869847a · audit A · 3 stars
client-communication SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/client-communication/SKILL.md · Use this skill when communicating with clients, freelance customers, or external stakeholders — scoping projects…
git:20260320.869847a · audit A · 3 stars
code-explanation SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/code-explanation/SKILL.md · Use this skill when writing code comments, explaining code decisions, documenting the "why" behind implementation…
git:20260320.869847a · audit A · 3 stars
code-reading SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/code-reading/SKILL.md · Use this skill when navigating unfamiliar codebases, understanding legacy code, onboarding to a new project, or…
git:20260320.869847a · audit A · 3 stars
code-review SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/code-review/SKILL.md · Use this skill when performing code reviews, security audits, architecture reviews, vulnerability analysis, or…
git:20260320.869847a · audit A · 3 stars
cross-functional-collab SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/cross-functional-collab/SKILL.md · Use this skill when working with designers, product managers, business stakeholders, or non-technical team members…
git:20260320.869847a · audit A · 3 stars
database-design SKILL.md skill
jamestorrevillas/dev-skills · .github/skills/database-design/SKILL.md · Use this skill when designing database schemas, choosing between SQL and NoSQL, optimizing queries, designing indexes…
git:20260320.869847a · audit A · 3 stars

Every file in jamestorrevillas/dev-skills

Other files named copilot-instructions.md

copilot-instructions.md
career-ops-hq/career-ops · .github/copilot-instructions.md
git:20261118.8c713f9 · audit A · 83,636 stars
copilot-instructions.md
greensock/gsap-skills · .github/copilot-instructions.md
git:20260309.96c4b01 · audit A · 18,706 stars
copilot-instructions.md
ar9av/obsidian-wiki · .github/copilot-instructions.md
git:20261105.7ae5ed7 · audit A · 3,781 stars
copilot-instructions.md
zaxbyhub/opencode-swarm · .github/copilot-instructions.md
git:20260605.393aac7 · audit A · 536 stars
copilot-instructions.md
yschimke/compose-ai-tools · .github/copilot-instructions.md
git:20260828.3c45998 · audit A · 130 stars
copilot-instructions.md
royerlab/luxar · .github/copilot-instructions.md
git:20260401.f251904 · audit B · 88 stars
copilot-instructions.md
andreaswasita/copilot-agents-dojo · .github/copilot-instructions.md
git:20260608.2eecb66 · audit A · 55 stars
copilot-instructions.md
vanshyadav1408/omentir · .github/copilot-instructions.md
git:20260828.d3bb9bc · audit A · 55 stars

Browse by kind, by grade A, or by owner.