agentleFS
lbusselllbussell/agent-skills/AGENTS.md

agent-skills

AGENTS.md0 starsChanged 8 days agoMITView on GitHub

In general, keep SKILL.md files under 50 lines. If extra information is necessary (references, scripts), put them in sub-folders: Treat the frontmatter description as the skill's trigger. The description should have two short sentences: Agents will decide whether to load the skill from the description alone. Therefore, the skill body should not contain qualifiers about when to use the skill. Use simplified technical english for agent instructions. Start skills small with the minimum amount of content. Only add content over…

  • 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 repository8 other files it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If extra information is necessary (references, scripts), put them in sub-folders:

    line 6
  2. Very specific:

    Treat the frontmatter description as the skill's trigger.

    line 19
  3. Distinctive:

    Use simplified technical english for agent instructions.

    line 30
  4. Distinctive:

    Start skills small with the minimum amount of content.

    line 31
  5. Distinctive:

    Only add content over time as necessary to improve agent performance on specific tasks.

    line 32

≈ “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

Skill authoring

Layout

In general, keep SKILL.md files under 50 lines. If extra information is necessary (references, scripts), put them in sub-folders:

skill-name/
  SKILL.md
  references/
    some-reference.md
  scripts/
    do-the-thing.ps1

Frontmatter

Treat the frontmatter description as the skill's trigger. The description should have two short sentences:

  1. What the skill does.
  2. Exactly when to use it.

Agents will decide whether to load the skill from the description alone. Therefore, the skill body should not contain qualifiers about when to use the skill.

Content

Use simplified technical english for agent instructions. Start skills small with the minimum amount of content. Only add content over time as necessary to improve agent performance on specific tasks.

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.