agentleFS
lookfreelookfree/claude-skills-factory/CLAUDE.md

claude-skills-factory

CLAUDE.md1 starsChanged 11 months agoMITView on GitHub

A curated collection of high-quality Claude Code skills for AI-assisted development workflows. Skills are modular components that extend Claude's capabilities for specific tasks. Each skill follows a standard structure: Planned skills: - API Documentation Generator - Test Case Generator - Refactoring Assistant - Performance Profiler - Security Auditor - Database Query Optimizer - Git Commit Message Generator - Architecture Analyzer MIT License - free to use in any project.

The file

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

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Very specific:

    Create directory with kebab-case name: mkdir my-new-skill

    line 75
  2. Very specific:

    Add SKILL.md with frontmatter (name, description)

    line 76
  3. Distinctive:

    Add README.md with usage instructions

    line 77
  4. Distinctive:

    Update root README.md with new skill entry

    line 80
  5. Distinctive:

    Tested: Verify triggers and output format

    line 88
  6. Distinctive:

    Use standard library only when possible

    line 97
  7. Distinctive:

    Use emoji sparingly and consistently

    line 102

≈ “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 Skills Factory

Project Overview

A curated collection of high-quality Claude Code skills for AI-assisted development workflows. Skills are modular components that extend Claude's capabilities for specific tasks.

Project Structure

claude-skills-factory/
├── README.md              # Main project documentation
├── CONTRIBUTING.md        # Contribution guidelines
├── LICENSE                # MIT License
├── .gitignore
├── code-review-assistant/ # Code review skill
│   ├── SKILL.md           # Skill definition (required)
│   ├── README.md          # User documentation
│   └── scripts/           # Helper scripts
│       └── complexity_checker.py
└── excalidraw/            # Architecture diagram generator
    ├── SKILL.md           # Skill definition
    └── README.md          # User documentation

Skill Architecture

Each skill follows a standard structure:

skill-name/
├── SKILL.md          # Main skill definition (required)
├── README.md         # Skill documentation (optional)
├── scripts/          # Helper scripts (optional)
│   └── *.py, *.sh
└── examples/         # Usage examples (optional)

SKILL.md Format

---
name: skill-name
description: Brief English description. 中文描述
---
# Skill Content

Available Skills

SkillDescription
code-review-assistantCode review for PRs and snippets (6-dimension analysis)
excalidrawGenerate architecture diagrams as .excalidraw files from codebase analysis

Development Commands

# Install skill locally (symlink)
ln -s $(pwd)/skill-name ~/.claude/skills/skill-name

# Install all skills
for skill in */; do
  ln -s $(pwd)/$skill ~/.claude/skills/$skill
done

# Copy skill to Claude skills directory
cp -r ./skill-name ~/.claude/skills/

# Run complexity checker (code-review-assistant)
python code-review-assistant/scripts/complexity_checker.py /path/to/code

Creating New Skills

  1. Create directory with kebab-case name: mkdir my-new-skill
  2. Add SKILL.md with frontmatter (name, description)
  3. Add README.md with usage instructions
  4. (Optional) Add helper scripts in scripts/
  5. (Optional) Add examples in examples/
  6. Update root README.md with new skill entry

Skill Guidelines

  • Naming: lowercase, hyphen-separated (e.g., code-review-assistant)
  • Bilingual: Include English and Chinese in description/content
  • Focused: One skill = one specific task
  • Documented: Clear usage instructions and examples
  • Tested: Verify triggers and output format

Coding Standards

Python Scripts

  • Python 3.6+ compatible
  • PEP 8 style
  • Include shebang: #!/usr/bin/env python3
  • Handle errors gracefully with helpful messages
  • Use standard library only when possible

Markdown

  • ATX-style headers (#)
  • Fenced code blocks with language tags
  • Use emoji sparingly and consistently

Roadmap

Planned skills:

  • API Documentation Generator
  • Test Case Generator
  • Refactoring Assistant
  • Performance Profiler
  • Security Auditor
  • Database Query Optimizer
  • Git Commit Message Generator
  • Architecture Analyzer

Key Files

FilePurpose
README.mdProject overview and installation
CONTRIBUTING.mdDetailed contribution guidelines
*/SKILL.mdSkill definition files
*/README.mdIndividual skill documentation

License

MIT License - free to use in any project.

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.