agentleFS
Sign inStart free
catesandrewcatesandrew/skills/AGENTS.md

skills

AGENTS.md1 starsChanged 5 days agoMITView on GitHub

Guidance for AI coding agents (Claude Code, Codex, Cursor, etc.) working in this repository. A public, personal collection of cross-agent skills, published both as an Agent Skills library (installable via the skills CLI) and as a self-hosted Claude Code plugin marketplace (.claude-plugin/marketplace.json). This is the public sibling of next-starters's own skills/ plugin: that repo keeps skills coupled to its Next.js starter templates; this repo holds everything stack-agnostic. 1. SKILL.md frontmatter must have name (kebab-case, matches directory) and description (starts with…

The file

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

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Keep SKILL.md under 500 lines.

    line 40
  2. Very specific:

    If installed via the skills CLI, re-run skills add -g catesandrew/skills after changes to update the local installation.

    line 48
  3. Very specific:

    No hardcoded employer/client names, internal org URLs, or absolute machine paths (/Users/<name>/...) — this repo is public.

    line 55

≈ “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

AGENTS.md

Guidance for AI coding agents (Claude Code, Codex, Cursor, etc.) working in this repository.

Repository Overview

A public, personal collection of cross-agent skills, published both as an Agent Skills library (installable via the skills CLI) and as a self-hosted Claude Code plugin marketplace (.claude-plugin/marketplace.json).

This is the public sibling of next-starters's own skills/ plugin: that repo keeps skills coupled to its Next.js starter templates; this repo holds everything stack-agnostic.

Directory Structure

skills/                       # this repo
  README.md                   # human-readable overview
  AGENTS.md                   # this file
  LICENSE
  .claude-plugin/
    marketplace.json          # plugin manifest listing every skill path
  skills/
    {skill-name}/              # kebab-case, matches the `name` field in SKILL.md
      SKILL.md                 # required: frontmatter (name, description) + instructions
      README.md                # optional: human-readable docs
      metadata.json             # optional: version, author, abstract, references
      references/ or rules/     # optional: supplementary reference material

Creating or Editing a Skill

  1. SKILL.md frontmatter must have name (kebab-case, matches directory) and description (starts with "Use when...", states triggering conditions, not the workflow).
  2. Keep SKILL.md under 500 lines. Move heavy reference material to a references/ directory.
  3. Variables use ${input:variableName:default} syntax for user-provided inputs.
  4. Regenerate .claude-plugin/marketplace.json by running node bin/generate-marketplace.mjs --prefix cw (it is fully generated from skills/ — do not hand-edit it), and add a row to the appropriate table in README.md (hand-maintained).
  5. If installed via the skills CLI, re-run skills add -g catesandrew/skills after changes to update the local installation.

Skill Quality Bar

  • Descriptions are third-person, start with "Use when...", and describe triggering conditions only (not the workflow).
  • No hardcoded employer/client names, internal org URLs, or absolute machine paths (/Users/<name>/...) — this repo is public. Parameterize with ${input:...} instead, or keep the skill in a private collection.
  • Each skill has a "Common Mistakes" section where applicable.
  • Chrome DevTools skills note they require the Chrome DevTools MCP server.

Session dossiers

Working-session write-ups (what changed, why, lessons, follow-ups) live in .sessions/<DATE>-<slug>/, produced by the session-wrap skill. Latest:

  • 2026-11-05-import-cursor-skills — imported 4 cursor-team-kit skills (MIT) with generated packages, catalog and docs pages
  • 2026-09-02-skills-docs-site — Docusaurus docs site, 52 archaeology-grounded deep-dive pages, deployed to skills.catesworks.dev
  • 2026-08-28-public-skills-repo-launch — repo creation + initial 49-skill migration from dotfiles

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