agentleFS
rohitgollarahallirohitgollarahalli/claude-skills/CLAUDE.md

claude-skills

CLAUDE.md0 starsChanged 5 months agoMITView on GitHub

Guidance for Claude (and contributors) when working in this repository. A collection of generic Agent Skills for software engineering and product work. Each skill lives in skills/<name>/ and is self-contained. The repo doubles as a Claude Code plugin marketplace via .claude-plugin/marketplace.json. Every skill must follow these, because consistency is what makes the collection trustworthy and the skills reliably triggerable: 1. Frontmatter has exactly two required fields: name and description. - name is lowercase with hyphens and matches the folder name.…

The file

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

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

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every skill must follow these, because consistency is what makes the collection trustworthy and the skills reliably triggerable:

    line 28
  2. Very specific:

    Create skills/<name>/SKILL.md following the conventions above.

    line 49
  3. Very specific:

    Add supporting references/ or assets/ only if they earn their place.

    line 50
  4. Distinctive:

    Add a row to the table in README.md.

    line 54
  5. Very specific:

    Every path listed in marketplace.json exists and contains a SKILL.md.

    line 69
  6. Very specific:

    Every SKILL.md has valid YAML frontmatter with name (matching its folder) and a description.

    line 70

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

CLAUDE.md

Guidance for Claude (and contributors) when working in this repository.

What this repo is

A collection of generic Agent Skills for software engineering and product work. Each skill lives in skills/<name>/ and is self-contained. The repo doubles as a Claude Code plugin marketplace via .claude-plugin/marketplace.json.

Repository layout

.
├── .claude-plugin/marketplace.json   # marketplace + plugin/bundle definitions
├── skills/
│   └── <skill-name>/
│       ├── SKILL.md                  # required: frontmatter + instructions
│       ├── references/               # optional: docs loaded on demand
│       └── assets/                   # optional: templates/files used in output
├── README.md
├── CLAUDE.md
└── LICENSE

Conventions for SKILL.md

Every skill must follow these, because consistency is what makes the collection trustworthy and the skills reliably triggerable:

  1. Frontmatter has exactly two required fields: name and description.
    • name is lowercase with hyphens and matches the folder name.
    • description states both what the skill does and when to use it, including concrete trigger phrases. This field is the sole mechanism that decides whether the skill fires, so make it specific and slightly "pushy" — list the phrasings a real user would type, and note that it should fire even when they don't name the skill explicitly.
  2. Instructions use the imperative mood and explain the why, not just the what. These models reason well; a rule with its rationale generalizes far better than a bare ALWAYS/NEVER.
  3. Keep SKILL.md focused (aim < ~200 lines). Push long lookup material into references/ and point to it from the body so it loads only when needed.
  4. Include a short, concrete example showing the expected output shape.
  5. Add a Guardrails section covering honesty (never fabricate results/data), scope, and failure modes.

Adding a new skill

  1. Create skills/<name>/SKILL.md following the conventions above.
  2. Add supporting references/ or assets/ only if they earn their place.
  3. Register the skill in .claude-plugin/marketplace.json under the right bundle (software-engineering-skills or product-skills), or add a new bundle if it's a new category.
  4. Add a row to the table in README.md.
  5. Validate before committing (see below).

Quality bar

A skill belongs here only if it is generic and genuinely useful — something people would reuse across many projects. A thin wrapper around a single API, or something a person would just do themselves in one session, doesn't meet the bar. Prefer a few excellent skills over many shallow ones.

Validation

Before committing, confirm:

  • python -c "import json; json.load(open('.claude-plugin/marketplace.json'))" parses.
  • Every path listed in marketplace.json exists and contains a SKILL.md.
  • Every SKILL.md has valid YAML frontmatter with name (matching its folder) and a description.

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.