How do I use SkillForge?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SkillForge save a skill: always use f-strings in Python" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

SkillForge

by CatVinci-Studio

Overview Schema Related Servers Score Discussions

Python

Local

✨ What is SkillForge?

SkillForge is a Model Context Protocol (MCP) server that gives your AI agent a persistent, evolving skill library. Instead of repeating the same corrections and preferences every session, SkillForge captures them as skills — structured instructions that the agent loads and follows automatically.

💡 Think of it as muscle memory for your AI — it learns your conventions once and applies them forever.

🔄 The Feedback Loop

  👤 User gives feedback
        │
        ▼
  🔍 Agent detects improvement signal
        │
        ▼
  🔀 Triage: reuse / improve / create?
        │
        ▼
  ✏️ Draft skill following guide + plan
        │
        ▼
  🛡️ Validation gate (reject or pass)
        │
        ▼
  💾 Skill saved (auto-backed up)
        │
        ▼
  ✅ Next task uses improved skill

Related MCP server: mcp_coordinator

🚀 Quick Start

📦 Installation

# Install from PyPI (recommended)
pip install skillforge-mcp

# Or with uv
uv pip install skillforge-mcp

⚡ Run the Server

# Run directly
skillforge

# Or run without installing via uvx
uvx skillforge-mcp

🔌 Connect to Claude Code

Add to your MCP config:

{
  "mcpServers": {
    "skillforge": {
      "command": "uvx",
      "args": ["skillforge-mcp"]
    }
  }
}

git clone https://github.com/CatVinci-Studio/skillForge.git
cd skillForge
pip install -e .

🧩 Architecture

src/skillforge/
├── 🏠 server.py              # MCP server definition & prompts
├── 📨 response.py            # Response formatting & feedback monitor
├── 🛡️ validator.py           # Hard validation gates for skill quality
├── 📁 skill_manager.py       # Core CRUD, backup, restore logic
├── 🔧 tools/
│   ├── 🔍 discovery.py       # list_skills, get_skill
│   ├── ✏️  crud.py            # save_skill (with validation), delete_skill
│   ├── 💾 backup.py          # list_backups, restore_skill
│   ├── 🔀 triage.py          # triage_skill_request
│   └── 🧠 optimization.py    # get_skill_guide, request_skill_optimization
└── 📖 guide/
    └── skill_writing_guide.md # Best practices for skill authoring

📂 Runtime Data

SkillForge stores its data in ~/.skillforge/:

Directory	Purpose
`~/.skillforge/skills/`	📚 Active skill library
`~/.skillforge/backups/`	🗄️ Automatic version history

🔒 Override with SKILLFORGE_SKILLS_DIR and SKILLFORGE_BACKUP_DIR environment variables.

🔧 Available Tools

Tool	Description
🔍 `list_skills`	List all skills — mandatory first call before any task
📖 `get_skill`	Load full skill instructions by name
🔀 `triage_skill_request`	Check existing skills before creating/improving — prevents duplication
🧠 `request_skill_optimization`	Get a structured plan for skill improvement
📖 `get_skill_guide`	Load the skill writing best practices guide
✏️ `save_skill`	Create or update a skill — validates and rejects if quality is insufficient
🗑️ `delete_skill`	Remove a skill (two-step confirmation, auto-backup)
📋 `list_backups`	View version history for a skill
⏪ `restore_skill`	Roll back to a previous version
📊 `get_optimization_history`	View the feedback log that drove skill changes

🛡️ Quality Gates (v0.2.0)

Unlike prompt-based quality control that depends on LLM compliance, SkillForge enforces quality through hard validation gates in save_skill:

Check	Type	Rule
📏 Description length	❌ Error	Must be ≥ 50 characters
📏 Body length	❌ Error	Must be 3–500 lines
🔄 Description ≠ name	❌ Error	Description must explain, not repeat the name
🎯 Trigger conditions	⚠️ Warning	Should include "when/whenever/use this skill..."
🗣️ Rigid language	⚠️ Warning	Prefer reasoning over "YOU MUST ALWAYS" imperatives
📐 Description too long	⚠️ Warning	Keep under 1000 chars, move details to body

🔴 Errors block the save — fix them and retry. 🟡 Warnings allow the save but flag areas for improvement.

🔀 Skill Triage

Before creating a new skill, triage_skill_request returns all existing skills so the LLM can decide:

Decision	Condition	Action
REUSE	Existing skill covers the need	Load it with `get_skill`
IMPROVE	Existing skill partially covers it	Optimize with `request_skill_optimization`
CREATE	No relevant skill exists	Create via `request_skill_optimization`

📝 Skill Format

Each skill lives in its own directory as a SKILL.md file with YAML frontmatter:

---
name: my-skill
description: >
  What this skill does and when to trigger it.
  Use this skill whenever the user asks for...
  Also activate when...
---

# Skill Instructions

Your markdown instructions here...

🏷️ Frontmatter Fields

Field	Required	Description
`name`	✅	Identifier (`lowercase-with-hyphens`, max 64 chars)
`description`	✅	Trigger conditions — WHAT it does + WHEN to use it (≥ 50 chars)
`disable-model-invocation`	❌	`true` = only user can invoke
`user-invocable`	❌	`false` = only LLM can invoke
`allowed-tools`	❌	Tools allowed without per-use approval
`context`	❌	`fork` = run in isolated sub-agent

🧠 How Optimization Works

SkillForge continuously monitors conversations for improvement signals:

Signal	Example	Action
🔴 Correction	"No, don't mock the database"	Update relevant skill
🟡 Preference	"Always use snake_case"	Create or update skill
🔵 Pattern	Same structure used 3+ times	Bundle into new skill
🟢 Explicit	"Add this to the review skill"	Direct skill edit

🔒 Safety Guarantees

✅ Auto-backup before every save and delete
✅ One-click restore from any backup timestamp
✅ Path traversal protection on all file operations
✅ Atomic writes with file locking for optimization logs
✅ Hard validation gates — quality enforced at the tool boundary, not by prompt

🌟 Why SkillForge?

Without SkillForge	With SkillForge
😤 Repeat the same corrections every session	🧠 Agent remembers and applies automatically
📋 Conventions scattered across docs	📦 Single source of truth per topic
🎲 Inconsistent agent behavior	✅ Deterministic, skill-guided responses
🔄 No learning from feedback	📈 Skills evolve with every interaction
🤞 Hope the LLM follows quality guidelines	🛡️ Hard validation rejects low-quality skills

🛣️ Roadmap

🛡️ Hard validation gates for skill quality
🔀 Skill triage to prevent duplication
🌐 Skill sharing & import from remote repositories
📊 Analytics dashboard for skill usage & effectiveness
🔗 Cross-skill dependency management
🧪 Skill testing framework with evaluation harness
🏪 Community skill marketplace

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License — see the LICENSE file for details.

Install Server

license - permissive license

quality

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

0dRelease cycle

2Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

View all tools

Related MCP Servers

cell-mem
Knowledge & Memory Autonomous Agents
Aether-liusiqi
A
license
-
quality
B
maintenance
An MCP server that provides AI agents with persistent, multi-layered memory inspired by the human brain, including consolidation, self-reflection, and generative replay.
Last updated 2026-06-09
1
MIT
mcp_coordinator
Coding Agents Autonomous Agents Code Execution
angrysky56
A
license
-
quality
B
maintenance
A self-improving coding agent MCP server that enables code execution, semantic memory, and reusable skills via sub-agents, turning your AI client into a meta-operating system.
Last updated 2026-05-05
2
AGPL 3.0
MCP Agent Skills Server
Code Execution Autonomous Agents Command Line
sqweeet
A
license
-
quality
D
maintenance
A production-ready MCP server that equips AI agents with dynamic, persistent, and executable skills. It enables secure script execution and progressive disclosure to reduce context window usage.
Last updated 2025-12-20
6
MIT
local-agent-context
Knowledge & Memory Developer Tools
TomiwaPhilip
A
license
-
quality
D
maintenance
A local MCP server that gives AI coding agents persistent memory and context across sessions.
Last updated 2026-03-27
11
MIT

View all related MCP servers

Related MCP Connectors

Motecloud Memory
Cloud-hosted MCP server for durable AI memory
Danushkumar-V-mcp-discord
An MCP server that integrates with Discord to provide AI-powered features.
driflyte-mcp-server
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CatVinci-Studio/skillForge'

If you have feedback or need assistance with the MCP directory API, please join our Discord server