Install
$ agentstack add skill-alirezarezvani-claudeforge-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
CLAUDE.md File Enhancer
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.
Capabilities
- 🆕 Interactive Initialization: Intelligent workflow that explores your repository, detects project type and tech stack, asks for confirmation, then creates customized CLAUDE.md files
- ✨ 100% Native Format Compliance: All generated files follow official Claude Code format with project structure diagrams, setup instructions, architecture sections, and file structure explanations (matching
/update-claude-mdslash command) - Analyze Existing Files: Scan and evaluate current CLAUDE.md files for structure, completeness, and quality
- Validate Best Practices: Check against Anthropic guidelines (file length, required sections, formatting standards)
- Generate New Files: Create complete CLAUDE.md files from scratch for new projects
- Enhance Existing Files: Add missing sections, improve structure, and update to latest best practices
- Modular Architecture: Support context-specific CLAUDE.md files in subdirectories (backend/, frontend/, docs/)
- Tech Stack Customization: Tailor guidelines to specific technologies (TypeScript, Python, Go, React, Vue, etc.)
- Team Size Adaptation: Adjust complexity based on team size (solo, small 3 major components
- Include tech stack reference immediately
- Add workflow instructions before team grows beyond 5 people
For Enhancement
- Analyze before modifying - understand current structure first
- Preserve custom content - only enhance, don't replace
- Validate after changes - ensure improvements don't break existing patterns
- Test with Claude Code - verify guidelines work as intended
General Guidelines
- Keep root file concise - Max 150 lines, use as navigation hub
- Use context-specific files - backend/CLAUDE.md, frontend/CLAUDE.md, etc.
- Avoid duplication - Each guideline should appear once
- Link to external docs - Don't copy official documentation
- Update regularly - Review guidelines quarterly or when stack changes
Limitations
Technical Constraints
- Requires valid project context for accurate template selection
- Tech stack detection is based on keywords, may need manual refinement
- Modular file generation assumes standard directory structure
Scope Boundaries
- Focuses on CLAUDE.md structure, not project-specific business logic
- Best practice recommendations are general, may need industry-specific customization
- Validation is guideline-based, not enforcement (no automated fixes without approval)
When NOT to Use
- For non-Claude AI tools (this is Claude Code specific)
- For projects that don't use Claude Code or similar AI assistants
- When you need highly specialized domain guidelines (legal, medical compliance)
Template Categories
By Size (single CLAUDE.md cap: 150 lines)
- Minimal (≤ 75 lines) - Solo developers, prototypes, hackathons
- Core (≤ 100 lines) - Small teams, MVPs, standard projects
- Detailed (≤ 125 lines) - Medium teams, production systems
- Comprehensive (≤ 150 lines + modular sub-files) - Large teams, enterprise; spread detail across chained sub-CLAUDE.md files instead of growing the root
By Project Type
- Web App - Frontend-focused (React, Vue, Angular)
- API - Backend services (REST, GraphQL, microservices)
- Full-Stack - Integrated frontend + backend
- CLI - Command-line tools and utilities
- Library - Reusable packages and frameworks
- Mobile - React Native, Flutter, native iOS/Android
By Tech Stack
- TypeScript/Node - Modern JavaScript ecosystem
- Python - Django, FastAPI, Flask
- Go - Gin, Echo, native services
- Java/Kotlin - Spring Boot, enterprise Java
- Ruby - Rails, Sinatra
Quality Metrics
File Quality Score (0-100)
Calculated based on:
- Length appropriateness (25 points) - Not too short or long
- Section completeness (25 points) - Required sections present
- Formatting quality (20 points) - Proper markdown structure
- Content specificity (15 points) - Tailored to project, not generic
- Modular organization (15 points) - Uses subdirectory files when appropriate
Recommendations Priority
- Critical - Missing required sections, file too long (>400 lines)
- High - Missing important sections, formatting issues
- Medium - Could add optional sections, minor improvements
- Low - Nice-to-have enhancements, stylistic suggestions
Advanced Features
Modular Architecture Support
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)
Tech Stack Detection
Automatically detects technologies from:
package.json(Node.js/TypeScript)requirements.txtorpyproject.toml(Python)go.mod(Go)Cargo.toml(Rust)pom.xmlorbuild.gradle(Java)
Team Size Adaptation
Adjusts detail level:
- Solo: Minimal guidelines, focus on efficiency
- Small (<10): Core guidelines, workflow basics
- Medium (10-50): Detailed guidelines, team coordination
- Large (50+): Comprehensive guidelines, process enforcement
References
- Anthropic Claude Code Docs: https://docs.claude.com/en/docs/claude-code
- CLAUDE.md Best Practices: Based on community patterns and Anthropic guidance
- Example CLAUDE.md Files: See
examples/folder for 6 reference implementations covering different project types and team sizes
Version
Version: 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.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: alirezarezvani
- Source: alirezarezvani/ClaudeForge
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.