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: 223 production-ready skills across 9 domains with 298 Python automation tools, 416 reference guides, 23 agents, and 22 slash commands.

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:

Architecture Overview

Repository Structure

claude-code-skills/
├── .claude-plugin/            # Plugin registry (marketplace.json)
├── agents/                    # 23 agents across all domains
├── commands/                  # 22 slash commands (changelog, tdd, saas-health, prd, code-to-prd, plugin-audit, sprint-plan, etc.)
├── engineering-team/          # 36 core engineering skills + Playwright Pro + Self-Improving Agent + Security Suite
├── engineering/               # 36 POWERFUL-tier advanced skills (incl. AgentHub, self-eval)
├── product-team/              # 15 product skills + Python tools
├── marketing-skill/           # 44 marketing skills (7 pods) + Python tools
├── c-level-advisor/           # 34 C-level advisory skills (10 roles + orchestration)
├── project-management/        # 7 PM skills + Atlassian MCP
├── ra-qm-team/                # 14 RA/QM compliance skills
├── business-growth/           # 5 business & growth skills + Python tools
├── finance/                   # 3 finance skills + Python tools
├── eval-workspace/            # Skill evaluation results (Tessl)
├── standards/                 # 5 standards library files
├── templates/                 # Reusable templates
├── docs/                      # MkDocs Material documentation site
├── scripts/                   # Build scripts (docs generation)
└── 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: v2.2.0 (latest)

v2.2.0 Highlights:

• Security skills suite — 6 new engineering-team skills: adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection (5 Python tools, 4 reference guides)
• Self-eval skill — Honest AI work quality evaluation with two-axis scoring, score inflation detection, and session persistence
• Snowflake development — Data warehouse development, SQL optimization, and data pipeline patterns
• 223 total skills across 9 domains, 298 Python tools, 416 references, 23 agents, 22 commands
• MkDocs docs site expanded to 269 generated pages (301 HTML pages)

v2.1.2 (2026-03-10):

• Landing page generator now outputs Next.js TSX + Tailwind CSS by default (4 design styles, 7 section generators)
• Brand voice integration — landing page workflow uses marketing brand voice analyzer to match copy tone to design style
• 25 Python scripts fixed across all domains (syntax, dependencies, argparse)
• 237/237 scripts verified passing --help

v2.1.1 (2026-03-07):

• 18 skills optimized from 66-83% to 85-100% via Tessl quality review
• YAML frontmatter (name + description) added to all SKILL.md files
• 6 new agents + 5 slash commands, Gemini CLI support, MkDocs docs site

v2.0.0 (2026-02-16):

• 25 POWERFUL-tier engineering skills added (engineering/ folder)
• Plugin marketplace infrastructure (.claude-plugin/marketplace.json)
• Multi-platform support: Claude Code, OpenAI Codex, OpenClaw

Past Sprints: See documentation/delivery/ and CHANGELOG.md for history.

Roadmap

Phase 1-3 Complete: 223 production-ready skills deployed across 9 domains

• Engineering Core (36), Engineering POWERFUL (36), Product (15), Marketing (44), PM (7), C-Level (34), RA/QM (14), Business & Growth (5), Finance (3)
• 298 Python automation tools, 416 reference guides, 23 agents, 22 commands
• Complete enterprise coverage from engineering through regulatory compliance, sales, customer success, and finance
• MkDocs Material docs site with 269+ indexed pages for SEO

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

ClawHub Publishing Constraints

This repository publishes skills to ClawHub (clawhub.com) as the distribution registry. The following rules are non-negotiable:

1. cs- prefix for slug conflicts only. When a skill slug is already taken on ClawHub by another publisher, publish with the cs- prefix (e.g., cs-copywriting, cs-seo-audit). The cs- prefix applies only on the ClawHub registry — repo folder names, local skill names, and all other tools (Claude Code, Codex, Gemini CLI) remain unchanged.
2. Never rename repo folders or local skill names to match ClawHub slugs. The repo is the source of truth.
3. No paid/commercial service dependencies. Skills must not require paid third-party API keys or commercial services unless provided by the project itself. Free-tier APIs and BYOK (bring-your-own-key) patterns are acceptable.
4. Rate limit: 5 new skills per hour on ClawHub. Batch publishes must respect this. Use the drip timer (clawhub-drip.timer) for bulk operations.
5. plugin.json schema — ONLY these fields: name, description, version, author, homepage, repository, license, skills: "./". No extra fields.
6. Version follows repo versioning. ClawHub package versions must match the repo release version (currently v2.2.0+).

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 31, 2026 Version: v2.2.0 Status: 223 skills deployed across 9 domains, 28 marketplace plugins, docs site live