Skip to main content

🔨 SkillForge

Meta-Programming Framework for Claude Code

Transform Claude Code from a generic AI assistant into an expert team member who knows YOUR stack, YOUR conventions, and YOUR patterns.

Status Version Python Version License Claude Code PyPI

FeaturesWhy SkillForgeInstallationQuick StartDocumentationContributing


📋 Table of Contents


🎯 What is SkillForge?

SkillForge is an intelligent meta-programming framework that extends Claude Code's native skill system. It automatically generates, orchestrates, and continuously improves personalized skills tailored to YOUR development workflow.

In one sentence: SkillForge turns Claude Code into an expert developer who codes exactly the way YOU do, using YOUR stack, YOUR conventions, and YOUR patterns.

The Problem

Claude Code's native skills are powerful but generic:

  • ❌ Don't know YOUR tech stack (Next.js? FastAPI? Supabase?)
  • ❌ Don't know YOUR conventions (camelCase? Absolute imports? Feature-based structure?)
  • ❌ Don't learn from YOUR patterns (Always use Zod? Prefer server actions?)
  • ❌ No intelligent orchestration (Claude must guess which skills to load)
  • ❌ Static and never improve over time

The Solution

┌─────────────────────────────────────────────────────┐
│                    SkillForge                       │
├─────────────────────────────────────────────────────┤
│                                                     │
│  Generator      →  Creates personalized skills     │
│  Orchestrator   →  Loads the right skills smartly  │
│  Learner        →  Learns from your usage patterns │
│  Optimizer      →  Improves skills continuously    │
│                                                     │
└─────────────────────────────────────────────────────┘
                          ↓
              ~/.claude/skills/
              ├── nextjs-fullstack/      ← YOUR Next.js patterns
              ├── supabase-integration/  ← YOUR auth setup
              └── git-workflow/          ← YOUR commit style

💡 Why SkillForge?

Without SkillForge

You: "Create a login component with Supabase auth"

Claude Code:
├─ Uses generic knowledge (possibly outdated)
├─ Doesn't know if you use App Router or Pages Router
├─ Doesn't know your UI library (Tailwind? Material UI?)
├─ Doesn't know your state management (Zustand? Redux?)
├─ Generates generic code

Result: OK code, but you need 15-30 minutes to:
├─ Fix naming conventions
├─ Adjust import paths
├─ Modify styling approach
├─ Adapt to your patterns
└─ 🕐 Time wasted: 15-30 minutes

With SkillForge

You: "Create a login component with Supabase auth"

SkillForge (invisible, in milliseconds):
├─ Analyzes intent: "login component, Supabase, auth"
├─ Identifies skills: nextjs-fullstack + supabase-integration
├─ Loads YOUR personalized skills
└─ Claude receives perfect context

Claude Code generates:
├─ Next.js 15 App Router (you use this)
├─ Shadcn/ui components (your UI library)
├─ Zustand store (your state management)
├─ @/ import aliases (your convention)
├─ camelCase naming (your convention)
├─ Zod validation (learned pattern after 20+ uses)
├─ Error boundary wrapper (learned pattern)
└─ Feature-based structure (your preference)

Result: Production-ready code, 0 modifications needed ✅
🚀 Time saved: 100%

✨ Features

🎨 Smart Skill Generation

  • Interactive Wizard: Answer questions about YOUR preferences (naming, imports, patterns)
  • Template System: Pre-built templates for popular stacks (Next.js, Vue, React, FastAPI, etc.)
  • Documentation Fetching: Auto-fetches latest docs via Context7 MCP
  • Convention Injection: Every generated skill includes YOUR personal conventions

🧠 Intelligent Orchestration

  • Intent Analysis: Understands what you're trying to do
  • Smart Loading: Loads only relevant skills with token optimization
  • Progressive Disclosure: Loads metadata → core → full content as needed
  • Dependency Management: Automatically loads related skills

📊 Pattern Learning

  • Usage Tracking: Tracks every skill usage and outcome
  • Pattern Detection: Identifies YOUR recurring patterns (confidence-based)
  • Auto-Application: Updates skills when patterns reach 80%+ confidence
  • Cross-Project Learning: Learns from ALL your projects simultaneously

⚡ Continuous Optimization

  • Token Reduction: Compresses verbose content without losing meaning
  • Redundancy Detection: Identifies overlapping skills and suggests merges
  • Documentation Updates: Auto-updates with latest library versions
  • Unused Skill Detection: Suggests removal of rarely-used skills

🏗️ How It Works

Architecture Overview

┌──────────────────────────────────────────────────────────┐
│                     User Profile                         │
│              (YOUR preferences, global)                  │
│   ~/.claude/skills/skillforge/data/user_profile.json    │
│                                                          │
│   - Naming conventions (camelCase, PascalCase)          │
│   - Import style (absolute with @/)                     │
│   - Preferred libraries (Zustand, Zod, React Query)     │
│   - Code patterns (feature-based structure)             │
│   - Workflow (conventional commits)                     │
└──────────────────────────────────────────────────────────┘
                          ↓
                 Injected into every skill
                          ↓
┌──────────────────────────────────────────────────────────┐
│                   Generated Skills                       │
│            (Tech-specific + YOUR preferences)            │
│                ~/.claude/skills/                         │
│                                                          │
│   nextjs-fullstack/                                     │
│   ├─ SKILL.md          ← Next.js patterns + YOUR prefs  │
│   ├─ templates/        ← Code templates                 │
│   └─ docs/             ← Reference docs                 │
│                                                          │
│   supabase-integration/                                 │
│   └─ SKILL.md          ← Supabase setup + YOUR prefs    │
└──────────────────────────────────────────────────────────┘
                          ↓
                 Used at runtime per project
                          ↓
┌──────────────────────────────────────────────────────────┐
│                  Runtime (Per Project)                   │
│                                                          │
│   Project A: Next.js 15 + Supabase                      │
│   ├─ Loads: nextjs-fullstack + supabase-integration    │
│   └─ Applies: YOUR conventions to THIS project stack    │
│                                                          │
│   Project B: Vue.js + Firebase                          │
│   ├─ Loads: vue-spa + firebase-integration             │
│   └─ Applies: YOUR conventions to THIS project stack    │
└──────────────────────────────────────────────────────────┘

The Four Core Components

1. Generator

Creates personalized skills from templates + latest documentation + YOUR preferences.

User answers wizard questions
    
Fetch latest docs (Context7)
    
Process template with YOUR preferences
    
Generate SKILL.md (2000+ lines)

2. Orchestrator

Intelligently selects and loads the right skills for each request.

Analyze user request
    
Identify relevant skills
    
Calculate token budget
    
Progressive loading (metadata  core  full)
    
Claude executes with perfect context

3. Learner

Detects patterns in your usage and updates skills automatically.

Track every usage
    
After 10+ uses, detect patterns
    
If confidence  80%, apply pattern
    
Update skills automatically
    
Notify user of learned pattern

4. Optimizer

Continuously improves skills for performance and quality.

Analyze all skills weekly
    
Find optimization opportunities:
├─ Token reduction
├─ Redundancy removal
├─ Documentation updates
└─ Unused skills
    
Apply optimizations (with user approval)

📦 Installation

Prerequisites

  • Python 3.11 or higher
  • Claude Code installed
  • pipx (recommended) or pip

Install SkillForge

# Install globally using pipx (recommended)
pipx install skillforge

# Or using pip
pip install skillforge

Initialize

# Initialize SkillForge in Claude Code
skillforge install

This creates the SkillForge directory structure in ~/.claude/skills/skillforge/.


🚀 Quick Start

1. Run the Setup Wizard

Open Claude Code in your most representative project:

cd ~/projects/my-main-project
claude

In Claude Code, run the wizard:

> /sf:wizard

The wizard will:

  1. ✅ Ask about YOUR personal preferences (naming, imports, patterns)
  2. ✅ Detect your current project's tech stack (if applicable)
  3. ✅ Fetch latest documentation for your technologies
  4. ✅ Generate personalized skills in ~/.claude/skills/

Example wizard session:

╔════════════════════════════════════════════════╗
║  🧙 SkillForge Setup Wizard                    ║
║  Building YOUR personal development profile    ║
╚════════════════════════════════════════════════╝

🔍 Auto-detecting from current directory...
   /Users/you/projects/my-nextjs-app

✅ Detected:
   ├─ Next.js 15.0.0
   ├─ TypeScript 5.3
   ├─ Tailwind CSS
   └─ Supabase

Use these as defaults? [Y/n] Y

Great! Let me ask a few more questions about YOUR preferences...

1️⃣ YOUR naming convention for variables?
   [1] camelCase
   [2] snake_case
> 1

2️⃣ YOUR import style?
   [1] Absolute imports with alias (@/...)
   [2] Relative imports (../../...)
> 1

3️⃣ YOUR preferred state management?
   [1] Zustand
   [2] Redux Toolkit
   [3] Context API
> 1

... (8-10 more questions) ...

╔════════════════════════════════════════════════╗
║  ⚙️ Generating Skills...                       ║
╚════════════════════════════════════════════════╝

[1/3] 📦 Fetching Next.js documentation...
      └─ ✅ Documentation fetched (Context7)

[2/3] 🔨 Generating nextjs-fullstack skill...
      ├─ Processing template
      ├─ Injecting YOUR preferences
      ├─ Creating SKILL.md (2341 lines)
      └─ ✅ Skill generated

[3/3] 🔨 Generating supabase-integration skill...
      └─ ✅ Skill generated

✅ Setup Complete!

Skills installed:
  ~/.claude/skills/
  ├─ nextjs-fullstack/
  ├─ supabase-integration/
  └─ git-workflow/

Your skills will improve as you use them!

2. Use Claude Code Normally

SkillForge works invisibly in the background:

You: "Create a login component with Supabase auth"

[SkillForge automatically loads your personalized skills]

Claude Code: [generates perfect code using YOUR conventions]

3. Generate Additional Skills

When you work on projects with different stacks:

> /sf:generate vue-spa
> /sf:generate firebase-integration
> /sf:generate python-fastapi

📖 Usage

Available Commands

Core Commands

# Run the setup wizard (first time or update)
> /sf:wizard

# Generate a specific skill
> /sf:generate <skill-name>

# Generate skill from current project
> /sf:generate --from-current

# List all installed skills
> /sf:list

# View SkillForge status
> /sf:status

Analysis & Optimization

# Analyze skills and usage patterns
> /sf:analyze

# Optimize existing skills
> /sf:optimize

# Update skills with latest documentation
> /sf:update <skill-name>
> /sf:update --all

# Check for available updates
> /sf:update --check

Debug & Introspection

# Debug orchestration decisions
> /sf:introspect --orchestration

# Debug pattern learning
> /sf:introspect --learning

Skill Templates

SkillForge includes templates for popular stacks:

Frontend:

  • nextjs-fullstack - Next.js App Router full-stack
  • nextjs-pages - Next.js Pages Router
  • react-vite - React + Vite SPA
  • vue-spa - Vue.js 3 + Vite
  • svelte-kit - SvelteKit

Backend:

  • python-fastapi - FastAPI backend
  • python-django - Django
  • node-express - Express.js

Integration:

  • supabase-integration - Supabase (auth, db, storage)
  • firebase-integration - Firebase
  • postgresql-integration - PostgreSQL
  • mongodb-integration - MongoDB

Workflow:

  • git-workflow - Git conventions & commit style
  • testing-vitest - Vitest testing
  • testing-jest - Jest testing

🔧 Configuration

User Profile Structure

Your preferences are stored in ~/.claude/skills/skillforge/data/user_profile.json:

{
  "version": "1.0",
  "preferences": {
    "naming": {
      "variables": "camelCase",
      "components": "PascalCase",
      "constants": "UPPER_SNAKE_CASE"
    },
    "imports": {
      "style": "absolute",
      "alias": "@/"
    },
    "technologies": {
      "state_management": "Zustand",
      "validation": "Zod",
      "testing": "Vitest"
    },
    "patterns": {
      "folder_structure": "feature-based",
      "component_style": "functional",
      "async_handling": "async/await"
    },
    "workflow": {
      "git_commits": "conventional"
    }
  }
}

Manual Editing

You can manually edit your profile:

# Edit profile
code ~/.claude/skills/skillforge/data/user_profile.json

# Regenerate skills with new preferences
> /sf:wizard --update

🏛️ Architecture

Directory Structure

~/.claude/skills/skillforge/
│
├── SKILL.md                      # Entry point (meta-skill)
│
├── core/                         # Behavioral files
│   ├── SKILLFORGE.md            # Core configuration
│   ├── ORCHESTRATION.md         # Orchestration logic
│   ├── GENERATOR.md             # Generation system
│   ├── PATTERNS.md              # Pattern learning
│   └── MCP_INTEGRATION.md       # MCP integrations
│
├── generators/                   # Python generators
│   ├── wizard_engine.py         # Interactive wizard
│   ├── skill_generator.py       # Skill generator
│   └── doc_fetcher.py           # Context7 integration
│
├── analyzers/                    # Intelligence
│   ├── intent_analyzer.py       # Analyze requests
│   ├── skill_discovery.py       # Find relevant skills
│   ├── pattern_detector.py      # Detect patterns
│   └── skill_optimizer.py       # Optimize skills
│
├── templates/                    # Skill templates
│   ├── tech-stack/
│   │   ├── nextjs-fullstack.template
│   │   ├── react-spa.template
│   │   └── python-api.template
│   └── workflow/
│       └── git-workflow.template
│
└── data/                         # Persistent data
    ├── user_profile.json         # Your preferences
    ├── usage_analytics.json      # Usage stats
    └── learned_patterns.json     # Learned patterns

Integration with Claude Code

SkillForge extends Claude Code's native skill system:

Claude Code loads skills from ~/.claude/skills/

When you make a request:
1. SkillForge analyzes intent
2. Identifies relevant skills
3. Loads them with token optimization
4. Claude receives perfect context
5. SkillForge tracks usage for learning

MCP Integration (Context7)

SkillForge uses Context7 MCP server to fetch up-to-date documentation:

# Fetch latest Next.js docs
docs = context7_get_library_docs(
    library_id="/vercel/next.js",
    topic="App Router",
    tokens=2000
)

# Extract and use in skill generation
best_practices = extract_best_practices(docs)
code_examples = extract_code_examples(docs)

🗺️ Roadmap

Current Status: v1.0.0 Production Release 🚀

✅ Phase 1-10: Complete (100%)

Foundation & Core Systems

  • Core architecture design
  • Complete briefing documentation
  • Generator implementation (WizardEngine, SkillGenerator, TemplateProcessor, DocFetcher)
  • Orchestrator implementation (IntentAnalyzer, SkillDiscovery)
  • Learner implementation (UsageTracker, PatternDetector, LearningPipeline)
  • Optimizer implementation (SkillOptimizer)

User Interface & Commands

  • Slash commands system (10 commands: /sf:wizard, /sf:generate, /sf:analyze, etc.)
  • Visual output system (VERBOSE, COMPACT, SILENT modes)
  • Beautiful installation experience

Quality & Testing

  • Comprehensive test suite (unit, integration, e2e)
  • Test coverage implementation
  • Performance optimization

Documentation & Release

  • Complete user documentation
  • API documentation
  • README and guides
  • Package published to PyPI
  • Installation scripts
  • Production-ready v1.0.0

🔮 Future Enhancements (Post v1.0)

  • Additional framework templates (Vue, Angular, FastAPI, Django)
  • Web UI for skill management
  • Skill marketplace for sharing and collaboration
  • Advanced analytics dashboard
  • Multi-project skill sharing
  • Team collaboration features
  • Import/export profiles
  • CI/CD integration hooks
  • IDE extensions (VSCode, JetBrains)

🤝 Contributing

SkillForge is in production (v1.0.0) and we welcome contributions!

Ways to Contribute

  • 🐛 Report bugs: Open an issue
  • 💡 Suggest features: Start a discussion
  • 📝 Improve docs: Submit documentation PRs
  • 🔨 Add templates: Contribute skill templates for new stacks
  • 🧪 Test: Try SkillForge and provide feedback

Development Setup

# Clone repository
git clone https://github.com/yourusername/skillforge.git
cd skillforge

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Run linter
ruff check .

Contribution Guidelines

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit changes (git commit -m 'feat: add amazing feature')
  4. Push to branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

Please follow Conventional Commits for commit messages.


❓ FAQ

General Questions

Q: Is SkillForge free?
A: Yes, SkillForge is open-source and free to use under the MIT license.

Q: Does SkillForge require Claude Code?
A: Yes, SkillForge is specifically designed as an extension for Claude Code's native skill system.

Q: Does SkillForge work with other AI coding assistants?
A: Not currently. SkillForge is built specifically for Claude Code's skill architecture.

Q: Is my data private?
A: Yes. All your preferences, patterns, and skills are stored locally in ~/.claude/skills/. Nothing is sent to external servers except when fetching public documentation via Context7.

Usage Questions

Q: Do I need to run the wizard for each project?
A: No! Run the wizard once to set up YOUR preferences. Skills are global and reusable across all projects.

Q: What if my project uses a different stack?
A: Simply generate additional skills: /sf:generate vue-spa or /sf:generate python-fastapi. Your personal preferences are applied to every skill.

Q: Can I share skills with my team?
A: Yes! You can export your profile and skills, and team members can import them. Team collaboration features are planned for v1.1.

Q: How much disk space does SkillForge use?
A: Approximately 50-100MB depending on how many skills you generate.

Q: Does SkillForge slow down Claude Code?
A: No. The orchestration happens in milliseconds, and intelligent token optimization ensures optimal performance.

Technical Questions

Q: How does pattern learning work?
A: SkillForge tracks your usage across all projects. When a pattern appears consistently (80%+ confidence), it's automatically applied to your skills.

Q: Can I disable pattern learning?
A: Yes, you can configure this in your profile or use /sf:introspect --learning to review before application.

Q: How often are skills updated?
A: Documentation updates can be run manually (/sf:update --all) or scheduled weekly via the optimizer.

Q: Can I customize skill templates?
A: Yes! Templates are stored in ~/.claude/skills/skillforge/templates/ and can be edited or extended.


📄 License

MIT License - see LICENSE file for details.


🙏 Acknowledgments

  • Anthropic for Claude Code and the native skills system
  • Context Labs for Context7 MCP server
  • Community contributors who help improve SkillForge

🔗 Links


Built with ❤️ by developers, for developers

If SkillForge helps you, please ⭐ star the repo!

Report Bug · Request Feature · Join Discord

Release files for skillforge 1.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for skillforge 1.2.0
File Size Uploaded
skillforge-1.2.0.tar.gz 430.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for skillforge 1.2.0
File Interpreter ABI Platform
skillforge-1.2.0-py3-none-any.whl Python 3 none any Details

Total release size:692.7 kB

Release files / skillforge-1.2.0.tar.gz

Download URL skillforge-1.2.0.tar.gz
Size 430.1 kB
Tags Source
SHA-256 checksum
How to use checksums
76243f1d41c1f9c332dbdc48a87aa1113b37a45852c260c71d7b1533e04e936d
BLAKE2b-256 checksum
How to use checksums
23729226b8e6e53ca6dd9f4458224a352b31da05d6793196c83c729ac74e9fb0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.7

Release files / skillforge-1.2.0-py3-none-any.whl

Download URL skillforge-1.2.0-py3-none-any.whl
Size 262.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
cecd37896bfa363423c519d5a04b288571db7be14aab96916c12801c8c7fae2e
BLAKE2b-256 checksum
How to use checksums
0c5d9a5a30d9234ebbadf389496cf7858acba9336b1d0f1e2ff4c9af0d5ed77c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.7

Release history Release notifications | RSS feed

This release

1.2.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page