agentleFS
Sign inStart free
gtskevingtskevin/skill-guide/AGENTS.md

skill-guide

AGENTS.md1 starsChanged 6 months agoMITView on GitHub

Three-file CommonJS pipeline: scan-skills.js (data), skill-guide.js (presentation), skill-registry.js (online directories).

  • 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 repository2 other files it gives its agents.

The file

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

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    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:

    No network calls in scan-skills.js.

    line 39
  2. Distinctive:

    Use descriptive variable names.

    line 42
  3. Very specific:

    Run npm test before every commit — it covers syntax checks, unit tests, and scanner smoke tests.

    line 49
  4. Distinctive:

    No new npm dependencies.

    line 59

≈ “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

skill-guide/
├── scan-skills.js       # Scanner — scans skill dirs, parses SKILL.md frontmatter, outputs JSON
├── skill-guide.js       # Presentation — transforms scanner JSON into HTML slide decks
├── skill-registry.js    # Online registry — fetches curated skill lists from GitHub
├── bin/skill-guide      # npm bin entry point
├── SKILL.md             # Skill definition consumed by Claude Code / Codex
├── test/                # Unit and integration tests (node:test)
│   ├── scan-skills.test.js
│   ├── cli.test.js
│   ├── registry.test.js
│   ├── translate.test.js
│   └── wrapped.test.js
├── docs/                # Analysis notes and design documents
└── agents/openai.yaml   # Agent configuration

Three-file CommonJS pipeline: scan-skills.js (data), skill-guide.js (presentation), skill-registry.js (online directories).

Build, Test, and Development Commands

npm test                              # Full CI gate: syntax check + unit tests + smoke tests
node --test test/*.test.js            # Unit tests only
node scan-skills.js --list            # List discovered skills (JSON)
node skill-guide.js --open            # Generate HTML guide and open in browser
node skill-guide.js --doctor          # Diagnose skill paths and environment
node skill-guide.js --lang zh --open  # Chinese UI output

Coding Style & Naming Conventions

  • Zero npm dependencies — use only Node.js built-ins (fs, path, os, crypto, child_process).
  • scan-skills.js must remain a single file — do not split into modules.
  • No network calls in scan-skills.js; skill-registry.js may fetch from GitHub via curl.
  • CommonJS (require/module.exports), 'use strict' at top of every file.
  • Requires Node.js >= 18 (uses node:test, node:assert/strict).
  • Use descriptive variable names; follow existing patterns in each file.

Testing Guidelines

  • Framework: Node.js built-in test runner (node:test) with node:assert/strict.
  • Each test creates an isolated temp directory as a fake $HOME with SKILL.md fixtures.
  • CI runs on Node 18/20/22 across Ubuntu and macOS.
  • Run npm test before every commit — it covers syntax checks, unit tests, and scanner smoke tests.

Commit & Pull Request Guidelines

  • Conventional commits: feat:, fix:, docs:, test:, refactor:.
  • Branch naming: feat/your-feature, fix/your-fix.
  • PRs must include: summary, test plan (npm test passes, manual CLI test), and a constraints checklist (no new deps, scan-skills.js stays one file, no network calls in scanner).

Constraints Checklist

  • No new npm dependencies.
  • scan-skills.js stays one file.
  • Scanner reads local files only (no network calls).
  • SKILL.md frontmatter follows Claude Code conventions (name, description, allowed-tools).

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