Analyzes, generates, and enhances CLAUDE.md files for any project type using best practices, modular architecture support, and tech stack customization. Use when setting up new projects, improving existing CLAUDE.md files, or establishing AI-assisted development standards.
npxskills add alirezarezvani/claude-code-skill-factory--skill claude-md-enhancerLoading…
This skill provides comprehensive CLAUDE.md file generation and enhancement for Claude Code projects. It analyzes existing files, validates against best practices, and generates customized guidelines tailored to your project type, tech stack, and team size.
/update-claude-md slash command)Provide existing CLAUDE.md file content or file path:
{
"mode": "enhance",
"file_path": "CLAUDE.md",
"content": "[existing CLAUDE.md content]",
"project_context": {
"type": "web_app",
"tech_stack": ["typescript", "react", "node", "postgresql"],
"team_size": "small",
"phase": "mvp"
}
}
Provide project context:
{
"mode": "create",
"project_context": {
"type": "api",
"tech_stack": ["python", "fastapi", "postgresql", "docker"],
"team_size": "medium",
"phase": "production",
"workflows": ["tdd", "cicd", "documentation_first"]
},
"modular": true,
"subdirectories": ["backend", "database", "docs"]
}
web_app, api, fullstack, cli, library, mobile, desktop)["typescript", "react", "node"])solo, small (<10), medium (10-50), large (50+)prototype, mvp, production, enterprise)tdd, cicd, documentation_first, agile, etc.){
"analysis": {
"file_size": 450,
"line_count": 320,
"sections_found": [
"Quick Navigation",
"Core Principles",
"Tech Stack",
"Workflow Instructions"
],
"missing_sections": [
"Testing Requirements",
"Error Handling Patterns"
],
"issues": [
{
"type": "length_warning",
"severity": "medium",
"message": "File exceeds recommended 300 lines (320 lines)"
},
{
"type": "missing_section",
"severity": "low",
"message": "Consider adding 'Testing Requirements' section"
}
],
"quality_score": 75,
"recommendations": [
"Split into modular files (backend/CLAUDE.md, frontend/CLAUDE.md)",
"Add testing requirements section",
"Reduce root file to <150 lines"
]
}
}
Complete CLAUDE.md file content or specific sections to add:
# CLAUDE.md
This file provides guidance for Claude Code when working with this project.
## Quick Navigation
- [Backend Guidelines](backend/CLAUDE.md)
- [Frontend Guidelines](frontend/CLAUDE.md)
- [Database Operations](database/CLAUDE.md)
- [CI/CD Workflows](.github/CLAUDE.md)
## Core Principles
1. **Test-Driven Development**: Write tests before implementation
2. **Type Safety First**: Use TypeScript strict mode throughout
3. **Component Composition**: Favor small, reusable components
4. **Error Handling**: Always handle errors with proper logging
5. **Documentation Updates**: Keep docs in sync with code changes
[... additional sections based on template ...]
Hey Claude—I just added the "claude-md-enhancer" skill. I don't have a CLAUDE.md file yet. Can you help me create one for this project?
What Happens:
Interactive Flow:
Hey Claude—I just added the "claude-md-enhancer" skill. Can you analyze my current CLAUDE.md file and tell me what's missing or could be improved?
Hey Claude—I just added the "claude-md-enhancer" skill. Can you create a CLAUDE.md file for my TypeScript React project with a team of 5 developers? We use PostgreSQL, Docker, and follow TDD practices.
Hey Claude—I just added the "claude-md-enhancer" skill. Can you enhance my existing CLAUDE.md by adding missing sections and improving the structure? Here's my current file: [paste content]
Hey Claude—I just added the "claude-md-enhancer" skill. Can you create a modular CLAUDE.md setup for my full-stack project? I need separate files for backend (Python/FastAPI), frontend (React), and database (PostgreSQL).
When CLAUDE.md doesn't exist in your project, this skill provides an intelligent initialization workflow:
Step 1: Detection
Step 2: Repository Exploration
explore commandStep 3: Intelligent Analysis
Step 4: User Confirmation ✋
Step 5: File Creation
Step 6: Enhancement
Step 7: Summary
User: "I need a CLAUDE.md for this project"
Claude: "I'll explore your repository first to understand the project.
[Explores using built-in commands]
Based on my exploration, here's what I discovered:
Project Type: Full-Stack Application
Tech Stack: TypeScript, React, Node.js, PostgreSQL, Docker
Team Size: Small (2-9 developers)
Development Phase: MVP
Workflows: TDD, CI/CD
Recommended Structure: Modular architecture
- Root CLAUDE.md (navigation hub)
- backend/CLAUDE.md (API guidelines)
- frontend/CLAUDE.md (React guidelines)
Would you like me to create these files?"
User: "Yes, please proceed"
Claude: "Creating customized CLAUDE.md files...
✅ Created CLAUDE.md (100 lines)
✅ Created backend/CLAUDE.md (150 lines)
✅ Created frontend/CLAUDE.md (175 lines)
Your project is ready for AI-assisted development!"
Manages the interactive initialization workflow for new projects.
Key Functions:
check_claude_md_exists() - Detect if CLAUDE.md existsgenerate_exploration_prompt() - Guide Claude to explore repositoryanalyze_discoveries() - Analyze exploration resultsgenerate_confirmation_prompt() - Create user confirmation promptget_workflow_steps() - Get complete workflow stepsAnalyzes existing CLAUDE.md files to identify structure, sections, and quality issues.
Key Functions:
analyze_file() - Parse and analyze CLAUDE.md structuredetect_sections() - Identify present and missing sectionscalculate_quality_score() - Score file quality (0-100)generate_recommendations() - Provide actionable improvement suggestionsValidates CLAUDE.md files against best practices and Anthropic guidelines.
Key Functions:
validate_length() - Check file length (warn if >300 lines)validate_structure() - Verify required sections presentvalidate_formatting() - Check markdown formatting qualityvalidate_completeness() - Ensure critical information includedGenerates new CLAUDE.md content or missing sections based on templates.
Key Functions:
generate_root_file() - Create main CLAUDE.md orchestratorgenerate_context_file() - Create context-specific files (backend, frontend, etc.)generate_section() - Generate individual sections (tech stack, workflows, etc.)merge_with_existing() - Add new sections to existing filesSelects appropriate template based on project context.
Key Functions:
select_template() - Choose template based on project type and team sizecustomize_template() - Adapt template to tech stackdetermine_complexity() - Calculate appropriate detail levelrecommend_modular_structure() - Suggest subdirectory organization"Always validate your output against official native examples before declaring complete."
Before finalizing any CLAUDE.md generation:
/update-claude-md slash command formatexamples/ folderCalculated based on:
Automatically generates context-specific files:
project-root/
├── CLAUDE.md # Root orchestrator (100-150 lines)
├── backend/
│ └── CLAUDE.md # Backend-specific (150-200 lines)
├── frontend/
│ └── CLAUDE.md # Frontend-specific (150-200 lines)
├── database/
│ └── CLAUDE.md # Database operations (100-150 lines)
└── .github/
└── CLAUDE.md # CI/CD workflows (100-150 lines)
Automatically detects technologies from:
package.json (Node.js/TypeScript)requirements.txt or pyproject.toml (Python)go.mod (Go)Cargo.toml (Rust)pom.xml or build.gradle (Java)Adjusts detail level:
examples/ folder for 6 reference implementations covering different project types and team sizesVersion: 1.0.0 Last Updated: November 2025 Compatible: Claude Code 2.0+, Claude Apps, Claude API
Remember: The goal is to make Claude more efficient and context-aware, not to create bureaucracy. Start simple, iterate based on real usage, and automate quality checks where possible.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).