agentleFS
Sign inStart free
paultyngpaultyng/skill-issue/CLAUDE.md

skill-issue

CLAUDE.md8 starsChanged 3 months agoMITView on GitHub

Personal user-level Claude Code skills, rules, and settings. The canonical clone (this repo) is the source of truth; ~/.claude/ is populated by ./install.sh. Use /create-skill and /create-rule respectively. Do not author SKILL.md or rule files from scratch. This repo must remain portable and free of company-specific content:

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

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Use /create-skill and /create-rule respectively.

    line 19
  2. Distinctive:

    No internal URLs, proprietary tool names, or org-specific workflows in skills, rules, or settings.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 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

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Repo Is

Personal user-level Claude Code skills, rules, and settings. The canonical clone (this repo) is the source of truth; ~/.claude/ is populated by ./install.sh.

Repository Structure

  • skills/ — Multi-step agent workflows (SKILL.md per directory). See .claude/rules/skill-authoring.md for conventions.
  • rules/ — Behavioral rules that auto-load every session. See .claude/rules/rule-authoring.md for conventions.
  • scripts/ — Shell scripts including statusline.
  • settings.merge.json — Curated keys merged into ~/.claude/settings.json (model, permissions, hooks, plugins).
  • install.sh — Install/sync script.

Creating Skills and Rules

Use /create-skill and /create-rule respectively. Do not author SKILL.md or rule files from scratch.

Sync workflow

  • ~/.claude/ is populated by ./install.sh running from this canonical clone.
  • Edits to skills/, rules/, scripts/, and top-level files in this repo flow into ~/.claude/ on each install.
  • Personal/local skills/rules/scripts in ~/.claude/ are preserved (never deleted).
  • settings.json is jq-merged: specific keys (model, effortLevel, statusLine, enabledPlugins, extraKnownMarketplaces, permissions.allow, hooks) flow from settings.merge.json; everything else stays user-local.

Portability

This repo must remain portable and free of company-specific content:

  • No internal URLs, proprietary tool names, or org-specific workflows in skills, rules, or settings.
  • Skills that need org-specific context should read it from project-level CLAUDE.md, REVIEW.md, or .claude/rules/ at runtime.
  • MCP tool references use fully qualified names (ServerName:tool_name).

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