agentleFS
Sign inStart free
mkarami313mkarami313/Claude-skill/CLAUDE.md

Claude-skill

CLAUDE.md0 starsChanged 13 days agoMITView on GitHub

This repo is a source of Claude skills and a Claude Code plugin marketplace.

The file

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

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Keep SKILL.md lean; move long checklists to references/ and runnable code to scripts/, loaded or run only when needed.

    line 12
  2. Distinctive:

    No README inside a skill folder — documentation goes in the root README.

    line 13
  3. Very specific:

    Add the skill to marketplace.json and to the table in README.md, and bump metadata.version.

    line 14
  4. Very specific:

    Every skill has tests/<name>/scenarios.md.

    line 16

≈ “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 repo is a source of Claude skills and a Claude Code plugin marketplace.

Layout

  • skills/<name>/SKILL.md — one folder per skill; optional scripts/ and references/ inside it.
  • .claude-plugin/marketplace.json — one plugin entry per skill ("source": "./", "strict": false, "skills": ["./skills/<name>"]).
  • README.md — the skills table and install instructions.

Adding or changing a skill

  1. Folder name = name in the SKILL.md frontmatter (kebab-case). The description says what the skill does and when to use it.
  2. Keep SKILL.md lean; move long checklists to references/ and runnable code to scripts/, loaded or run only when needed.
  3. No README inside a skill folder — documentation goes in the root README.
  4. Add the skill to marketplace.json and to the table in README.md, and bump metadata.version.
  5. Everything in this repo is written in English.
  6. Every skill has tests/<name>/scenarios.md; after changing a skill, walk through each scenario with the new SKILL.md and check the expected behaviour still holds.
  7. Scripts: bash with set -u, LF line endings, bash -n clean; Python 3 standard library only.

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