agentleFS
DrawdEADrawdEA/dev-shortcuts/CLAUDE.md

dev-shortcuts

CLAUDE.md1 starsChanged 7 months agoMITView on GitHub

Claude Code skills package. Installs via npx github:DrawdEA/dev-shortcuts or node bin/install.js. Three Claude Code skills for pre-ship guardrails: - /sanity-check — npm package/pattern health check (hits live npm + GitHub + community sentiment) - /stack-check — architecture review across fit, coherence, longevity, AI coding compat - /ship-check — pre-release audit: secrets, console.logs, build check, auto-fix loop Skills live in ~/.claude/skills/ after install. Claude Code picks them up automatically. bin/install.js checks for Python 3, then copies the files listed in files[]…

The file

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

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

  • 4

    Very specific

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

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

    Create <skill-name>/SKILL.md with YAML frontmatter (name, description, triggers)

    line 31
  2. Very specific:

    Add any scripts under <skill-name>/scripts/

    line 32
  3. Very specific:

    Add the files to the files array in bin/install.js

    line 33
  4. Very specific:

    Add the dir to files in package.json

    line 34

≈ “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

dev-shortcuts

Claude Code skills package. Installs via npx github:DrawdEA/dev-shortcuts or node bin/install.js.

What this is

Three Claude Code skills for pre-ship guardrails:

  • /sanity-check — npm package/pattern health check (hits live npm + GitHub + community sentiment)
  • /stack-check — architecture review across fit, coherence, longevity, AI coding compat
  • /ship-check — pre-release audit: secrets, console.logs, build check, auto-fix loop

Skills live in ~/.claude/skills/ after install. Claude Code picks them up automatically.

Project structure

bin/install.js          ← copies skill files to ~/.claude/skills/
sanity-check/SKILL.md   ← skill definition + trigger instructions
sanity-check/scripts/   ← scan_deps.py
stack-check/SKILL.md
ship-check/SKILL.md
ship-check/scripts/     ← audit.py, fixer.py, build_check.py

Install flow

bin/install.js checks for Python 3, then copies the files listed in files[] to ~/.claude/skills/. No npm deps required at runtime.

Adding a skill

  1. Create <skill-name>/SKILL.md with YAML frontmatter (name, description, triggers)
  2. Add any scripts under <skill-name>/scripts/
  3. Add the files to the files array in bin/install.js
  4. Add the dir to files in package.json
  5. Document in README

Requirements

  • Node.js >=14
  • Python 3.x (for sanity-check and ship-check scripts)
  • Claude Code (Pro, Max, Team, or Enterprise)

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.