agentleFS
Sign inStart free
cloverinkcloverink/shipwright/CLAUDE.md

shipwright

CLAUDE.md0 starsChanged 49 days agoMITView on GitHub

Conventions for adding or editing skills in this repo. All skills live flat under skills/<skill-name>/SKILL.md. No bucket grouping: this matches Claude Code's skill-discovery convention and keeps every skill discoverable at one level. Agents live under agents/<name>.md. The one shipped agent, code-reviewer (Opus, read-only), is the only reviewer skills should spawn: skills pass it a lens instead of defining their own reviewer. Every skill must have: Every agent must be listed in plugin.json agents and keep read-only tools if it reviews.

The file

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

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    All skills live flat under skills/<skill-name>/SKILL.md.

    line 7
  2. Distinctive:

    Every skill must have:

    line 14
  3. Very specific:

    Every agent must be listed in plugin.json agents and keep read-only tools if it reviews.

    line 19
  4. Very specific:

    Use shorthand model names (opus, sonnet, haiku), not full IDs.

    line 23

≈ “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

Shipwright: Contributor Rules

Conventions for adding or editing skills in this repo.

Layout

All skills live flat under skills/<skill-name>/SKILL.md. No bucket grouping: this matches Claude Code's skill-discovery convention and keeps every skill discoverable at one level.

Agents live under agents/<name>.md. The one shipped agent, code-reviewer (Opus, read-only), is the only reviewer skills should spawn: skills pass it a lens instead of defining their own reviewer.

Required References

Every skill must have:

  1. A row in the top-level README.md skills table
  2. An entry in .claude-plugin/plugin.json skills list

Every agent must be listed in plugin.json agents and keep read-only tools if it reviews.

SKILL.md Frontmatter

Use shorthand model names (opus, sonnet, haiku), not full IDs.

---
name: my-skill
description: One-line summary used for skill discovery
model: sonnet
---

Patterns Reference

Reusable design patterns live in patterns/. When introducing a new skill, check if an existing pattern applies: link to it from the skill's SKILL.md instead of re-explaining.

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