agentleFS
tapanshahtapanshah/Claude-Skills/CLAUDE.md

Claude-Skills

CLAUDE.md0 starsChanged 12 months agoMITView on GitHub

This is a comprehensive skills library for Claude AI and Claude Code - reusable, production-ready skill packages that bundle domain expertise, best practices, analysis tools, and strategic frameworks. The repository provides modular skills that teams can download and use directly in their workflows. Current Scope: 134 production-ready skills across 9 domains with 185+ Python automation tools and 250+ reference guides. Key Distinction: This is NOT a traditional application. It's a library of skill packages meant to be extracted and deployed…

  • Reads credentials
  • Installs packages
  • Commits and pushes

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. Distinctive:

    Use standard library only (minimal dependencies)

    line 111
  2. Distinctive:

    No ML/LLM calls (keeps skills portable and fast)

    line 114
  3. Very specific:

    Keep scripts runnable with minimal setup (pip install package at most)

    line 117
  4. Very specific:

    Document all dependencies in SKILL.md

    line 118
  5. Distinctive:

    Prefer standard library implementations

    line 119
  6. Distinctive:

    Algorithm over AI: - Use deterministic analysis (code) vs LLM calls

    line 153
  7. Distinctive:

    Creating New Skills: Follow the appropriate domain's roadmap and CLAUDE.md guide (see Navigation Map above).

    line 167

≈ “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.

Project Purpose

This is a comprehensive skills library for Claude AI and Claude Code - reusable, production-ready skill packages that bundle domain expertise, best practices, analysis tools, and strategic frameworks. The repository provides modular skills that teams can download and use directly in their workflows.

Current Scope: 134 production-ready skills across 9 domains with 185+ Python automation tools and 250+ reference guides.

Key Distinction: This is NOT a traditional application. It's a library of skill packages meant to be extracted and deployed by users into their own Claude workflows.

Navigation Map

This repository uses modular documentation. For domain-specific guidance, see:

DomainCLAUDE.md LocationFocus
Agent Developmentagents/CLAUDE.mdcs-* agent creation, YAML frontmatter, relative paths
Marketing Skillsmarketing-skill/CLAUDE.mdContent creation, SEO, ASO, demand gen, campaign analytics
Product Teamproduct-team/CLAUDE.mdRICE, OKRs, user stories, UX research, SaaS scaffolding
Engineering (Core)engineering-team/CLAUDE.mdFullstack, AI/ML, DevOps, security, data, QA tools
Engineering (POWERFUL)engineering/Agent design, RAG, MCP, CI/CD, database, observability
C-Level Advisoryc-level-advisor/CLAUDE.mdCEO/CTO strategic decision-making
Project Managementproject-management/CLAUDE.mdAtlassian MCP, Jira/Confluence integration
RA/QM Compliancera-qm-team/CLAUDE.mdISO 13485, MDR, FDA, GDPR, ISO 27001 compliance
Business & Growthbusiness-growth/CLAUDE.mdCustomer success, sales engineering, revenue operations
Financefinance/CLAUDE.mdFinancial analysis, DCF valuation, budgeting, forecasting
Standards Librarystandards/CLAUDE.mdCommunication, quality, git, security standards
Templatestemplates/CLAUDE.mdTemplate system usage

Architecture Overview

Repository Structure

claude-code-skills/
├── .claude-plugin/            # Plugin registry (marketplace.json)
├── agents/                    # cs-* prefixed agents (in development)
├── marketing-skill/           # 7 marketing skills + Python tools
├── product-team/              # 8 product skills + Python tools
├── engineering-team/          # 22 core engineering skills + Python tools
├── engineering/               # 25 POWERFUL-tier advanced skills (v2.0.0)
├── c-level-advisor/           # 2 C-level skills
├── project-management/        # 6 PM skills + Atlassian MCP + packaged-skills
├── ra-qm-team/                # 12 RA/QM compliance skills
├── business-growth/           # 4 business & growth skills + Python tools
├── finance/                   # 1 finance skill + Python tools
├── standards/                 # 5 standards library files
├── templates/                 # Reusable templates
└── documentation/             # Implementation plans, sprints, delivery

Skill Package Pattern

Each skill follows this structure:

skill-name/
├── SKILL.md              # Master documentation
├── scripts/              # Python CLI tools (no ML/LLM calls)
├── references/           # Expert knowledge bases
└── assets/               # User templates

Design Philosophy: Skills are self-contained packages. Each includes executable tools (Python scripts), knowledge bases (markdown references), and user-facing templates. Teams can extract a skill folder and use it immediately.

Key Pattern: Knowledge flows from references/ → into SKILL.md workflows → executed via scripts/ → applied using assets/ templates.

Git Workflow

Branch Strategy: feature → dev → main (PR only)

Branch Protection Active: Main branch requires PR approval. Direct pushes blocked.

Quick Start

# 1. Always start from dev
git checkout dev
git pull origin dev

# 2. Create feature branch
git checkout -b feature/agents-{name}

# 3. Work and commit (conventional commits)
feat(agents): implement cs-{agent-name}
fix(tool): correct calculation logic
docs(workflow): update branch strategy

# 4. Push and create PR to dev
git push origin feature/agents-{name}
gh pr create --base dev --head feature/agents-{name}

# 5. After approval, PR merges to dev
# 6. Periodically, dev merges to main via PR

Branch Protection Rules:

  • ✅ Main: Requires PR approval, no direct push
  • ✅ Dev: Unprotected, but PRs recommended
  • ✅ All: Conventional commits enforced

See documentation/WORKFLOW.md for complete workflow guide. See standards/git/git-workflow-standards.md for commit standards.

Development Environment

No build system or test frameworks - intentional design choice for portability.

Python Scripts:

  • Use standard library only (minimal dependencies)
  • CLI-first design for easy automation
  • Support both JSON and human-readable output
  • No ML/LLM calls (keeps skills portable and fast)

If adding dependencies:

  • Keep scripts runnable with minimal setup (pip install package at most)
  • Document all dependencies in SKILL.md
  • Prefer standard library implementations

Current Version

Version: v2.0.0 (released 2026-02-16)

v2.0.0 Highlights:

  • 25 POWERFUL-tier engineering skills added (engineering/ folder)
  • Plugin marketplace infrastructure (.claude-plugin/marketplace.json)
  • VirusTotal security scanning for skills (CI)
  • Multi-platform support: Claude Code, OpenAI Codex, OpenClaw
  • Skills enhanced with production Python scripts and Anthropic best practices

Past Sprints: See documentation/delivery/ for sprint history.

Roadmap

Phase 1-2 Complete: 134 production-ready skills deployed across 9 domains

  • Marketing (7), C-Level (33), Product (8), PM (6), Engineering Core (23), Engineering Advanced (14), RA/QM (12), Business & Growth (4), Finance (1)
  • 160+ Python automation tools, 200+ reference guides
  • Complete enterprise coverage from marketing through regulatory compliance, sales, customer success, and finance

Next Priorities:

  • Phase 3 (Q2 2026): Marketing expansion - SEO optimizer, social media manager, growth marketer
  • Phase 4 (Q3 2026): Specialized domains - Mobile, blockchain, web3, advanced analytics

Target: 100+ skills by Q3 2026

See domain-specific roadmaps in each skill folder's README.md or roadmap files.

Key Principles

  1. Skills are products - Each skill deployable as standalone package
  2. Documentation-driven - Success depends on clear, actionable docs
  3. Algorithm over AI - Use deterministic analysis (code) vs LLM calls
  4. Template-heavy - Provide ready-to-use templates users customize
  5. Platform-specific - Specific best practices > generic advice

Anti-Patterns to Avoid

  • Creating dependencies between skills (keep each self-contained)
  • Adding complex build systems or test frameworks (maintain simplicity)
  • Generic advice (focus on specific, actionable frameworks)
  • LLM calls in scripts (defeats portability and speed)
  • Over-documenting file structure (skills are simple by design)

Working with This Repository

Creating New Skills: Follow the appropriate domain's roadmap and CLAUDE.md guide (see Navigation Map above).

Editing Existing Skills: Maintain consistency across markdown files. Use the same voice, formatting, and structure patterns.

Quality Standard: Each skill should save users 40%+ time while improving consistency/quality by 30%+.

Additional Resources

  • .gitignore: Excludes .vscode/, .DS_Store, AGENTS.md, PROMPTS.md, .env*
  • Plugin Registry: .claude-plugin/marketplace.json - Marketplace distribution
  • Standards Library: standards/ - Communication, quality, git, documentation, security
  • Implementation Plans: documentation/implementation/
  • Sprint Delivery: documentation/delivery/

Last Updated: March 2026 Version: v2.0.0 Status: 134 skills deployed across 9 domains, plugin marketplace active

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.