agentleFS
Sign inStart free
SvampenSvampen/claude-skills/CLAUDE.md

claude-skills

CLAUDE.md0 starsChanged 9 months agoMITView on GitHub

This repository contains reusable Claude Code skills that can be symlinked or copied into other projects. Each skill has a SKILL.md with: - Frontmatter: name, description, allowed-tools, user-invocable - When to Use: Trigger phrases and conditions - Instructions: Step-by-step workflow - Examples: Usage scenarios - Error Handling: Edge cases - Notes: Additional context

The file

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

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  1. Very specific:

    Use /git-commit skill when committing changes

    line 36
  2. Distinctive:

    Test skills in a separate project before merging

    line 37
  3. Very specific:

    Always include allowed-tools and user-invocable in frontmatter

    line 42
  4. Distinctive:

    Document trigger phrases clearly in "When to Use" section

    line 43
  5. Distinctive:

    Keep skills generic - project-specific config goes in user's project

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

Claude Skills Repository

This repository contains reusable Claude Code skills that can be symlinked or copied into other projects.

Repository Structure

claude-skills/
├── skills/                    # Source skill definitions
│   ├── git-commit/
│   ├── session-start/
│   ├── worktree-start/
│   └── ...
├── .claude/
│   └── skills/               # Symlinks to skills/ (for dogfooding)
├── CLAUDE.md                 # This file
├── README.md                 # User documentation
├── CONTRIBUTING.md           # Contributor guidelines
└── LICENSE                   # MIT License

Skill File Structure

Each skill has a SKILL.md with:

  • Frontmatter: name, description, allowed-tools, user-invocable
  • When to Use: Trigger phrases and conditions
  • Instructions: Step-by-step workflow
  • Examples: Usage scenarios
  • Error Handling: Edge cases
  • Notes: Additional context

Working on This Repo

  • Skills are in skills/ directory (source of truth)
  • .claude/skills/ contains symlinks for local testing
  • Use /git-commit skill when committing changes
  • Test skills in a separate project before merging

Conventions

  • Skill names: kebab-case (e.g., git-commit, session-start)
  • Always include allowed-tools and user-invocable in frontmatter
  • Document trigger phrases clearly in "When to Use" section
  • Keep skills generic - project-specific config goes in user's project

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.

Check your setup, free