agentleFS
Sign inStart free
DeanThompsonDeanThompson/agent-skills/AGENTS.md

agent-skills

AGENTS.md1 starsChanged 6 months agoMITView on GitHub

This repo is a public skill pack. Keep changes portable across agent runtimes.

  • 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 31,774 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 repository4 other files it gives its agents.

The file

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

12 rules. About 0 are common, 6 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    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. Very specific:

    Put installable skills under skills/<skill-name>/.

    line 7
  2. Very specific:

    Every skill must include SKILL.md with YAML frontmatter containing at least name and description.

    line 8
  3. Very specific:

    Keep SKILL.md focused on the core workflow and trigger guidance.

    line 9
  4. Very specific:

    Put deterministic helper code in scripts/.

    line 11
  5. Distinctive:

    Do not add per-skill README files unless a runtime explicitly requires them.

    line 12
  6. Distinctive:

    Prefer ASCII in docs and scripts unless the source skill is intentionally Chinese-language.

    line 13
  7. Distinctive:

    Do not assume a specific runtime in skill bodies.

    line 17
  8. Distinctive:

    Use "agent" or "runtime" unless a section is intentionally runtime-specific.

    line 18
  9. Very specific:

    Keep runtime-specific install notes in docs/compatibility.md.

    line 19
  10. Distinctive:

    Avoid runtime-specific frontmatter fields unless they are optional metadata.

    line 20
  11. Very specific:

    Do not commit secrets, local caches, .DS_Store, node_modules, or __pycache__.

    line 24
  12. Distinctive:

    Run the publishing checklist before committing release changes.

    line 27

≈ “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

Agent Instructions

This repo is a public skill pack. Keep changes portable across agent runtimes.

Conventions

  • Put installable skills under skills/<skill-name>/.
  • Every skill must include SKILL.md with YAML frontmatter containing at least name and description.
  • Keep SKILL.md focused on the core workflow and trigger guidance.
  • Move longer details to references/.
  • Put deterministic helper code in scripts/.
  • Do not add per-skill README files unless a runtime explicitly requires them.
  • Prefer ASCII in docs and scripts unless the source skill is intentionally Chinese-language.

Compatibility

  • Do not assume a specific runtime in skill bodies.
  • Use "agent" or "runtime" unless a section is intentionally runtime-specific.
  • Keep runtime-specific install notes in docs/compatibility.md.
  • Avoid runtime-specific frontmatter fields unless they are optional metadata.

Safety

  • Do not commit secrets, local caches, .DS_Store, node_modules, or __pycache__.
  • Preserve destructive-operation guardrails.
  • For CLI-backed skills, document prerequisites, authentication, and confirmation behavior.
  • Run the publishing checklist before committing release changes.

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