agentleFS
monegitmonegit/agent-skills/AGENTS.md

agent-skills

AGENTS.md0 starsChanged 31 days agoMITView on GitHub

This repository publishes reusable agent skills. The root README.md is the English catalog and README.ko.md its Korean translation. Store each skill in skills/<skill-name>/ with SKILL.md and an English README.md; add README.ko.md for bilingual documentation. Keep focused guidance in references/, for example skills/create-component/references/styling.md. Use lowercase kebab-case for directory and skill names. Keep the name in a skill's YAML frontmatter aligned with its directory. Write direct Markdown; organize SKILL.md around purpose, activation conditions, workflow, outputs, and guardrails. Link reference files using relative…

  • 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 repository3 other files it gives its agents.

The file

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

8 rules. About 0 are common, 4 are distinctive, and 4 are 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use lowercase kebab-case for directory and skill names.

    line 13
  2. Distinctive:

    Keep translated READMEs aligned with English examples, paths, and installation commands.

    line 18
  3. Very specific:

    When asked to update or refresh the README, first explore skills/ to identify the current skill directories and their documentation.

    line 23
  4. Very specific:

    Use this entry shape in the English README.

    line 34
  5. Distinctive:

    Treat each skill's written workflow as its test contract.

    line 77
  6. Very specific:

    Use the action-first format: <verb>(<skill-name>): <concise scope>.

    line 83
  7. Distinctive:

    Use one of these verbs:

    line 84
  8. Distinctive:

    Use the scope to name the concrete features or rules changed.

    line 88

≈ “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

Repository Guidelines

Project Structure & Module Organization

This repository publishes reusable agent skills. The root README.md is the English catalog and README.ko.md its Korean translation. Store each skill in skills/<skill-name>/ with SKILL.md and an English README.md; add README.ko.md for bilingual documentation. Keep focused guidance in references/, for example skills/create-component/references/styling.md.

Skill and Documentation Conventions

Use lowercase kebab-case for directory and skill names. Keep the name in a skill's YAML frontmatter aligned with its directory. Write direct Markdown; organize SKILL.md around purpose, activation conditions, workflow, outputs, and guardrails. Link reference files using relative paths.

Keep translated READMEs aligned with English examples, paths, and installation commands. Do not claim tooling or behavior absent from this repository.

README Skill Catalog Updates

When asked to update or refresh the README, first explore skills/ to identify the current skill directories and their documentation. Update the Skills section in README.md and the 스킬 목록 section in README.ko.md using the existing per-skill format: a linked heading, a GitHub NOTE information quote, key capabilities, activation conditions, and a fenced installation command.

List entries in ascending English alphabetical order by skill directory name. For example, create-component comes before monospec-kit. Add newly found skills, remove catalog entries for deleted skills, and ensure each link points to the correct language-specific skill README.

Use this entry shape in the English README; translate the labels and summary for README.ko.md while preserving the same structure:

### [<skill-name>](skills/<skill-name>/README.md)
> [!NOTE]
> <Short skill description.>

**Key capabilities**:

- <Capability 1>
- <Capability 2>
- <Capability 3>

**Use when**:

- <Activation condition 1>
- <Activation condition 2>

**Install**:

```sh
npx skills add https://github.com/monegit/agent-skills --skill <skill-name>
```

---

Build, Test, and Development Commands

There is no application build, package manifest, linter, or automated test suite. Use lightweight documentation checks before submitting changes:

rg --files skills
git diff --check
git diff -- README.md README.ko.md skills/<skill-name>

These commands confirm files, detect whitespace errors, and focus review.

Testing Guidelines

Treat each skill's written workflow as its test contract. Verify referenced files, repository paths, and output locations; consider both new and existing resource paths and document edge-case guardrails.

Commit & Pull Request Guidelines

  • Use the action-first format: <verb>(<skill-name>): <concise scope>.
  • Use one of these verbs:
    • add for a new skill, document, or capability.
    • update for a change to an existing skill or document.
    • remove for removing a skill, document, or capability.
  • Use the scope to name the concrete features or rules changed. When a commit changes multiple meaningful behaviors, include each distinguishing change in the scope.
    • For example: update(create-component): enforce styles and prohibit children usage.
  • Keep commits focused.

Pull requests should summarize user-facing changes, list modified skills, describe validation, and include before/after examples when behavior or output 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.