agentleFS
4444J994444J99/a-i--skills/.github/copilot-instructions.md

a-i--skills

Copilot instructions17 starsChanged 5 months agoApache-2.0Archived repositoryView on GitHub

This repository contains a collection of Claude skills that extend AI agent capabilities. Each skill is self-contained and documented through a SKILL.md file with YAML frontmatter. The AI Skills repository hosts specialized instructions, scripts, and resources for AI agents (Claude, Codex, Gemini CLI). Skills enable agents to perform tasks ranging from creative work to technical documentation and code analysis. Add a new skill: Validate changes: Release workflow: Use short, imperative messages with PR references:

1 other project uses a version of this.

The file

We split this copilot-instructions.md into the rules it gives an agent

11 rules. About 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Skill-First Architecture: Every skill must have a SKILL.md file with valid YAML frontmatter

    line 11
  2. Very specific:

    Single Catalog: All catalog skills live under skills/<category>/.

    line 14
  3. Distinctive:

    Naming Convention: Use lowercase kebab-case matching the directory name

    line 20
  4. Very specific:

    After Changes: Run python3 scripts/refresh_skill_collections.py

    line 29
  5. Very specific:

    Keep scripts self-contained within skill's scripts/ directory

    line 33
  6. Distinctive:

    Update README.md if adding/removing skills from curated lists

    line 39
  7. Very specific:

    Update THIRD_PARTY_NOTICES.md when adding external assets

    line 40
  8. Distinctive:

    Keep examples concise and actionable

    line 41
  9. Distinctive:

    Only install one collection at a time (avoid duplicate skill names)

    line 73
  10. Distinctive:

    No repo-wide test suite; run per-skill tests when they exist

    line 74
  11. Distinctive:

    Use short, imperative messages with PR references:

    line 80

≈ “Common” is an estimate: at least 1 in 5 of the 3,827 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
copilot-instructions.md

AI Skills Repository - GitHub Copilot Instructions

This repository contains a collection of Claude skills that extend AI agent capabilities. Each skill is self-contained and documented through a SKILL.md file with YAML frontmatter.

Repository Purpose

The AI Skills repository hosts specialized instructions, scripts, and resources for AI agents (Claude, Codex, Gemini CLI). Skills enable agents to perform tasks ranging from creative work to technical documentation and code analysis.

Key Principles

  • Skill-First Architecture: Every skill must have a SKILL.md file with valid YAML frontmatter
  • Self-Contained Design: Each skill directory is independent with its own resources
  • Generated Artifacts: Link directories and collections are committed and maintained by scripts
  • Single Catalog: All catalog skills live under skills/<category>/; Claude Code plugins live under plugins/

Code Assistance Guidelines

When Creating or Modifying Skills

  1. Naming Convention: Use lowercase kebab-case matching the directory name
  2. Required Frontmatter:
    ---
    name: skill-name
    description: Concise task-focused sentence
    ---
  3. Optional Fields: license, allowed-tools, metadata
  4. After Changes: Run python3 scripts/refresh_skill_collections.py

When Writing Python Scripts

  • Keep scripts self-contained within skill's scripts/ directory
  • Include simple smoke tests or usage examples
  • Reference environment variables for credentials (never commit secrets)

When Updating Documentation

  • Update README.md if adding/removing skills from curated lists
  • Update THIRD_PARTY_NOTICES.md when adding external assets
  • Keep examples concise and actionable

Common Workflows

Add a new skill:

# Create directory and SKILL.md with frontmatter
# Add any scripts or assets
python3 scripts/refresh_skill_collections.py
python3 scripts/validate_skills.py --collection example --unique

Validate changes:

python3 scripts/validate_skills.py --collection example --unique
python3 scripts/validate_generated_dirs.py
python3 -m pytest

Release workflow:

python3 scripts/release.py VERSION --change "Description" --commit --tag --push

Directory Structure Context

  • skills/, .codex/skills, .claude/skills, extensions/gemini/*/skills - Generated bundles
  • collections/ - Auto-generated skill path lists
  • scripts/ - Maintenance and validation scripts

Important Constraints

  • Only install one collection at a time (avoid duplicate skill names)
  • No repo-wide test suite; run per-skill tests when they exist
  • Skill name must exactly match directory name
  • Generated directories are committed artifacts

Commit Message Style

Use short, imperative messages with PR references:

Add accessibility-patterns skill (#42)
Update SKILL.md validation script
Clarify installation steps in README.md (#20)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.