agentleFS
4444J994444J99/a-i--skills/docs/AGENTS.md

a-i--skills

AGENTS.md17 starsChanged 5 months agoApache-2.0Archived repositoryView on GitHub

Global policy: /Users/4jp/AGENTS.md applies and cannot be overridden. This repository is a collection of example Claude skills. Each skill is self-contained in its own folder and is documented by a SKILL.md file with YAML frontmatter. Use this guide when adding or updating skills. Examples: - python3 -m pytest (repository tooling tests) - pip install -r mcp-builder/scripts/requirements.txt - pip install -r slack-gif-creator/requirements.txt - python3 scripts/refresh_skill_collections.py (regenerates collections and link dirs) - python3 scripts/validate_skills.py --collection example --unique - python3 scripts/refresh_skill_collections.py --mode symlink…

  • Installs packages

1 other project uses a version of this.

The file

We split this AGENTS.md into the rules it gives an agent

7 rules. About 1 is common, 4 are distinctive, and 2 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Keep examples concise and actionable.

    line 29
  2. Very specific:

    Place executable helpers under scripts/ and keep them self-contained.

    line 30
  3. Distinctive:

    No shared testing framework or coverage target is enforced.

    line 33
  4. Distinctive:

    If you add scripts, include a simple, runnable smoke check (command and expected behavior) in the skill instructions or a nearby README.

    line 34
  5. Distinctive:

    Commit messages are short, imperative, and often include a PR reference in parentheses (e.g., "Clarify Claude Code installation in …

    line 37
  6. Common:

    Do not commit secrets. Reference environment variables in scripts when external credentials are required.

    line 42
  7. Very specific:

    Keep third-party attributions updated in THIRD_PARTY_NOTICES.md when adding external assets or data.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md 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
AGENTS.md

Repository Guidelines

Global policy: /Users/4jp/AGENTS.md applies and cannot be overridden.

This repository is a collection of example Claude skills. Each skill is self-contained in its own folder and is documented by a SKILL.md file with YAML frontmatter. Use this guide when adding or updating skills.

Project Structure & Module Organization

  • Top-level docs: README.md (overview), agent_skills_spec.md (skill schema reference), and THIRD_PARTY_NOTICES.md.
  • Skill directories: one folder per skill (kebab-case name), each with a SKILL.md and optional references/, scripts/, assets/, or ooxml/ subfolders.
  • Generated collections: distributions/collections/example-skills.txt (one path per line).
  • Agent link dirs: skills/, .codex/skills, .claude/skills, and extensions/gemini/*/skills are generated by the refresh script.

Build, Test, and Development Commands

Repo-wide tooling tests run with python3 -m pytest (see tests/). Run per-skill scripts when needed.

Examples:

  • python3 -m pytest (repository tooling tests)
  • pip install -r mcp-builder/scripts/requirements.txt
  • pip install -r slack-gif-creator/requirements.txt
  • python3 scripts/refresh_skill_collections.py (regenerates collections and link dirs)
  • python3 scripts/validate_skills.py --collection example --unique
  • python3 scripts/refresh_skill_collections.py --mode symlink (optional symlink mode)
  • python3 scripts/validate_generated_dirs.py (ensures bundles are copied and in sync)

Coding Style & Naming Conventions

  • Skills are Markdown-first. Keep instructions in SKILL.md with YAML frontmatter:
    • name: lowercase kebab-case and should match the folder name.
    • description: short, task-focused, and written as a sentence.
  • Keep examples concise and actionable; prefer ASCII unless the content requires otherwise.
  • Place executable helpers under scripts/ and keep them self-contained.

Testing Guidelines

  • No shared testing framework or coverage target is enforced.
  • If you add scripts, include a simple, runnable smoke check (command and expected behavior) in the skill instructions or a nearby README.

Commit & Pull Request Guidelines

  • Commit messages are short, imperative, and often include a PR reference in parentheses (e.g., "Clarify Claude Code installation in README.md (#20)").
  • PRs should summarize affected skills, link relevant issues/docs, and call out any new dependencies. Update README.md if you add or remove skills from the curated lists.
  • Regenerated link directories and collections are committed artifacts; run the refresh script and include them in skill-change PRs.

Security & Configuration Tips

  • Do not commit secrets. Reference environment variables in scripts when external credentials are required.
  • Keep third-party attributions updated in THIRD_PARTY_NOTICES.md when adding external assets or data.

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.