agentleFS
Sign inStart free
LichAmnesiaLichAmnesia/lich-skills/CLAUDE.md

lich-skills

CLAUDE.md233 starsChanged 7 months agoMITView on GitHub

Guidance for Claude Code when working inside this repository. lich-skills is an open-source collection of Claude Code skills. Public, MIT-licensed. Three skills today: Every skill lives at skills/<name>/SKILL.md with YAML frontmatter: Follow the process-not-prose convention: clear steps, exit criteria, rationalization tables. feat|fix|refactor|docs|chore|ci|test + scope. English. Example: feat(tavily): add search skill.

  • Reads credentials

The file

We split this CLAUDE.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 secrets: Never commit API keys, tokens, .env files, service-account JSON.

    line 15
  2. Distinctive:

    MIT license: All new files inherit MIT.

    line 18
  3. Very specific:

    Every skill lives at skills/<name>/SKILL.md with YAML frontmatter:

    line 22
  4. Distinctive:

    Follow the process-not-prose convention: clear steps, exit criteria, rationalization tables.

    line 31

≈ “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 — lich-skills

Guidance for Claude Code when working inside this repository.

What this repo is

lich-skills is an open-source collection of Claude Code skills. Public, MIT-licensed. Three skills today:

  • spec-driven-dev — Spec → Plan → Build → Test → Review → Ship workflow
  • tavily-search — web search via the Tavily API
  • nano-banana — image generation/edit via Google's Nano Banana 2

Hard rules (repo is public)

  1. No secrets. Never commit API keys, tokens, .env files, service-account JSON. A gitleaks pre-commit hook runs on every commit — do not bypass it with --no-verify.
  2. Env vars only. Skills read credentials from environment variables (TAVILY_API_KEY, GEMINI_API_KEY, etc.). Never hardcode. Use YOUR_API_KEY_HERE in examples.
  3. No private file paths. Example paths in skill docs should be generic (~/project/, ./output.png) — never reference the author's private workspace.
  4. MIT license. All new files inherit MIT. Do not paste copyrighted code from other projects without attribution and license compatibility.

Skill format

Every skill lives at skills/<name>/SKILL.md with YAML frontmatter:

---
name: skill-name
description: One-line trigger description starting with "Use when..."
---

Follow the process-not-prose convention: clear steps, exit criteria, rationalization tables.

Conventional commits

feat|fix|refactor|docs|chore|ci|test + scope. English. Example: feat(tavily): add search skill.

Before every commit

  1. gitleaks detect --config .gitleaks.toml --source . — clean
  2. Skill runs locally (for script-backed skills)
  3. README skills table is up to date

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