agentleFS
Sign inStart free
overmentoverment/skills/AGENTS.md

skills

AGENTS.md31 starsChanged 22 days agoMITView on GitHub

This is a public repository of Agent Skills. Everything committed here is published.

  • Reads credentials
  • 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 31,700 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 repository8 other files it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Create or reshape skills with skills/skill-shaper.

    line 8
  2. Very specific:

    Keep skills portable: rely on Agent Skills spec fields, and mark any agent-specific field or tool name as such in the body.

    line 9
  3. Very specific:

    No personal paths, hostnames, private project names, credentials, or .env values in any skill, eval, or test.

    line 10
  4. Very specific:

    Every skill has evals/<name>.md with routing prompts that should and shouldn't trigger it.

    line 12
  5. Very specific:

    When a skill changes behaviour, bump metadata.version in its frontmatter and update its entry in the README list.

    line 13
  6. Distinctive:

    Every file the body links to exists.

    line 19
  7. Distinctive:

    Run the skill's evals in a fresh session when its description or behaviour changed.

    line 20

≈ “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

AGENTS.md

This is a public repository of Agent Skills. Everything committed here is published.

Rules

  • One skill per folder in skills/<name>/, and name in the frontmatter must match the folder.
  • Create or reshape skills with skills/skill-shaper. Follow its procedure rather than copying another skill's layout.
  • Keep skills portable: rely on Agent Skills spec fields, and mark any agent-specific field or tool name as such in the body.
  • No personal paths, hostnames, private project names, credentials, or .env values in any skill, eval, or test. Skills get installed on other people's machines.
  • Nothing written for humans inside a skill folder (README, CHANGELOG). The repository README describes the skills.
  • Every skill has evals/<name>.md with routing prompts that should and shouldn't trigger it.
  • When a skill changes behaviour, bump metadata.version in its frontmatter and update its entry in the README list.

Checks before committing

  • name is 1–64 lowercase letters, digits and single hyphens, and matches the folder.
  • description is one or two sentences of about 250 characters at most, third person, with no XML tags and no lists of examples. A "Not for…" clause only for a real near miss.
  • Every file the body links to exists.
  • Run the skill's evals in a fresh session when its description or behaviour changed.

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