agentleFS
Sign inStart free
mraspberrymraspberry/skills/AGENTS.md

skills

AGENTS.md0 starsChanged 3 months agoMITView on GitHub

  • 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 repository5 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, 8 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep each reusable skill self-contained in a top-level directory.

    line 3
  2. Distinctive:

    Add shared tooling at the repository root only when it applies to every skill.

    line 5
  3. Very specific:

    Write SKILL.md content as concise, direct Markdown.

    line 9
  4. Distinctive:

    Use title-case headings and ordered lists for skill conversation stages.

    line 10
  5. Very specific:

    Keep valid YAML frontmatter at the top of every SKILL.md.

    line 11
  6. Distinctive:

    Use lowercase kebab-case for skill directories and identifiers.

    line 14
  7. Distinctive:

    Keep guidance specific and avoid speculative dependencies.

    line 16
  8. Distinctive:

    Follow the sequence: capabilities, components, interactions, contracts, implementation.

    line 17
  9. Very specific:

    Run prek run --all-files after changes.

    line 22
  10. Very specific:

    Do not claim validation if prek is unavailable.

    line 23
  11. Distinctive:

    Use short, imperative Conventional Commit-style subjects.

    line 27
  12. Distinctive:

    Keep each commit focused on one skill or tooling concern.

    line 28

≈ “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

Project Structure

  • Keep each reusable skill self-contained in a top-level directory.
  • Include SKILL.md and agents/openai.yaml in every skill directory.
  • Add shared tooling at the repository root only when it applies to every skill.

Skill Authoring

  • Write SKILL.md content as concise, direct Markdown.
  • Use title-case headings and ordered lists for skill conversation stages.
  • Keep valid YAML frontmatter at the top of every SKILL.md.
  • Match each frontmatter name to its skill directory name.
  • State in each frontmatter description when the skill is explicitly invoked.
  • Use lowercase kebab-case for skill directories and identifiers.
  • Indent YAML with two spaces.
  • Keep guidance specific and avoid speculative dependencies.
  • Follow the sequence: capabilities, components, interactions, contracts, implementation.

Validation

  • Confirm edited frontmatter parses and instructions match the skill's scope.
  • Run prek run --all-files after changes.
  • Do not claim validation if prek is unavailable.

Commits And Pull Requests

  • Use short, imperative Conventional Commit-style subjects.
  • Keep each commit focused on one skill or tooling concern.
  • Summarize behavior, affected skills, implications, and validation in pull requests.

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