agentleFS
Sign inStart free
TokDar2410621TokDar2410621/superSkill/AGENTS.md

superSkill

AGENTS.md2 starsChanged 26 days agoMITView on GitHub

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. Darius-Tokam/superSkill★ 4100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository5 other files it gives its agents.

The file

We split this AGENTS.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:

    Every skill appears in .claude-plugin/plugin.json's skills array and in both language sections of README.md, its name linked to its …

    line 5
  2. Very specific:

    Every skill is either user-invoked (disable-model-invocation: true in SKILL.md plus policy.allow_implicit_invocation: false in …

    line 6
  3. Very specific:

    After touching a manifest, run claude plugin validate .

    line 8
  4. Distinctive:

    No em-dashes in any prose.

    line 10

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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

superSkill: repo conventions

  • Skills live flat under skills/<name>/. At 10 skills, regroup them into category folders (skills/<category>/<name>/), then update plugin.json, both README sections, and the Gemini install command.
  • Skill names are French, contents are English. A name uses only a-z, 0-9 and single hyphens (no accents: the Agent Skills spec rejects them), and matches its folder. display_name in agents/openai.yaml and the README may carry accents.
  • Every skill appears in .claude-plugin/plugin.json's skills array and in both language sections of README.md, its name linked to its SKILL.md.
  • Every skill is either user-invoked (disable-model-invocation: true in SKILL.md plus policy.allow_implicit_invocation: false in agents/openai.yaml) or model-invoked (neither). Every skill carries an agents/openai.yaml.
  • A skill reaches another by naming the Skill tool: Call the Skill tool with "interrogatoire". Only model-invoked skills can be reached this way.
  • After touching a manifest, run claude plugin validate . --strict. Bump version in plugin.json for each release: managed installs update only when it changes.
  • Adapted skills keep their upstream credit in README.md and LICENSE.
  • No em-dashes in any prose. Rewrite the sentence with a comma, colon, period, or parentheses.

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