⚡ FastSkills — Give Any Agent the Same Skill Engine Behind Claude, OpenClaw & nanobot.

The Problem

Claude Code, GitHub Copilot, OpenAI Codex, and Cursor all have a skill engine built in — the agent discovers SKILL.md playbooks, reads them on demand, and follows structured instructions to produce consistent, high-quality output. That's why they can generate professional documents, presentations, and code without being told how every time.

But the skill engine is locked inside each product.

If you're building with LangChain, CrewAI, AutoGen, Smolagents, or any custom agent — you get nothing. No skill discovery, no progressive disclosure, no structured playbooks. You'd have to build the entire engine from scratch.

The Solution

FastSkills extracts the skill engine into a standalone MCP server. One command gives any agent the same capability:

uvx fastskills --skills-dir ./skills

That's it. Your agent can now discover, read, and execute any SKILL.md — the same open standard used by Claude Code, Copilot, Codex, OpenClaw, and nanobot.

No framework adoption. No code changes. No SDK integration. Just MCP.

Before & After

WITHOUT FastSkills:

  Claude Code ──── has skill engine ──── can use 40,000+ skills
  Copilot     ──── has skill engine ──── can use 40,000+ skills
  Codex CLI   ──── has skill engine ──── can use 40,000+ skills
  OpenClaw    ──── has skill engine ──── can use 40,000+ skills
  nanobot     ──── has skill engine ──── can use 40,000+ skills
  ─────────────────────────────────────────────────────────────
  LangChain   ──── nothing           ──── ✗
  CrewAI      ──── nothing           ──── ✗
  AutoGen     ──── nothing           ──── ✗
  Your agent  ──── nothing           ──── ✗


WITH FastSkills:

  Any agent   ──── FastSkills (MCP) ──── can use 40,000+ skills ✓

Why Not Just Use OpenClaw or nanobot?

You can — and they're great. But they solve a different problem:

OpenClaw and nanobot are platforms — you adopt their agent, their runtime, their ecosystem. FastSkills is a building block — it gives your existing agent skill capabilities without replacing anything.

Quick Start

Connect any agent in 30 seconds

Add one block to your MCP client config (Claude Desktop, Cursor, VS Code, Windsurf, Goose, or any custom agent):

{
  "mcpServers": {
    "fastskills": {
      "command": "uvx",
      "args": ["fastskills", "--skills-dir", "/path/to/skills", "--workdir", "/path/to/output"]
    }
  }
}

Your agent now has skill discovery, skill reading, and a full execution toolkit (bash, file creation, string replacement) — matching the tool surface that Claude Code provides natively.

What's uvx? It's a tool from uv that runs Python packages in isolated environments — no install step needed. Install it with curl -LsSf https://astral.sh/uv/install.sh | sh or brew install uv.

Or use the built-in TUI

# Clone the repo
git clone https://github.com/nj19257/FastSkills.git
cd FastSkills

# Start chatting (requires uv: https://docs.astral.sh/uv/)
uv run fastskills_cli

On first launch you'll be prompted for your OpenRouter API key and model. The bundled 18 skills are automatically discovered.

How the Skill Engine Works

The same progressive disclosure pattern used by Claude Code, Copilot, and Codex:

 ┌──────┐    ┌──────┐    ┌──────┐    ┌────────┐    ┌─────────┐
 │ Scan │───►│Match │───►│ Read │───►│ Follow │───►│ Deliver │
 └──────┘    └──────┘    └──────┘    └────────┘    └─────────┘
  metadata    best fit    SKILL.md    run scripts    output
   ~100 tok   agent       full body   bash/create    consistent
   per skill  decides     on demand   on demand      quality

1. Scan — list_skills returns names + descriptions (~100 tokens per skill)
2. Match — The agent decides which skill fits the task
3. Read — view(path=...) reads the full SKILL.md into context
4. Follow — bash_tool runs scripts, file_create writes output
5. Deliver — Consistent, high-quality results every time

The agent only loads what it needs, when it needs it. No context window bloat.

System Prompt

FastSkills includes a gold-standard system prompt at prompt/gold_standard_prompt.yaml that teaches any agent the discover → read → execute workflow. Use it directly or reference it to build your own.

Architecture

┌─────────────────┐        MCP        ┌──────────────┐      filesystem     ┌──────────────┐
│   Your Agent    │◄────────────────►│  FastSkills   │◄──────────────────►│   skills/    │
│  (any MCP       │     protocol      │  MCP Server   │   read SKILL.md    │  ├── pptx/   │
│   client)       │                   │  (FastMCP)    │   run scripts      │  ├── docx/   │
└─────────────────┘                   └──────────────┘                     │  ├── pdf/    │
                                                                           │  └── ...     │
                                                                           └──────────────┘

Core Tools (always available)

Cloud Tools (require SKILLSMP_API_KEY)

To enable cloud tools, pass SKILLSMP_API_KEY via the MCP client config:

{
  "mcpServers": {
    "fastskills": {
      "command": "uvx",
      "args": ["fastskills", "--skills-dir", "/path/to/skills", "--workdir", "/path/to/output"],
      "env": {
        "SKILLSMP_API_KEY": "sk_live_your_key_here"
      }
    }
  }
}

Bundled Skills (18)

Add Your Own

Drop a folder with a SKILL.md into your skills directory. FastSkills picks it up automatically:

~/.fastskills/skills/
├── pptx/
│   └── SKILL.md
├── my-custom-skill/
│   ├── SKILL.md
│   ├── scripts/
│   │   └── generate.py
│   └── references/
│       └── style-guide.md
└── ...

---
name: api-documentation
description: Generate consistent API documentation following team standards.
  Use when writing docs for REST endpoints, SDKs, or internal APIs.
---

# API Documentation Skill

## When to Use
Use this skill when the user asks to document an API, generate endpoint
references, or create SDK documentation.

## Instructions
1. Read the source code or endpoint definitions
2. Extract parameters, return types, and error codes
3. Generate documentation following the template in ./references/template.md
4. Include code examples for each endpoint

Skill Sources

The MCP server loads skills from a single directory specified by --skills-dir. The TUI (fastskills_cli) auto-resolves from two locations:

You can also use skills from Anthropic's skills repo, SkillsMP (cloud catalog), or any community source.

The Agent Skills Ecosystem

FastSkills uses the same open standard adopted across the industry:

Skills are portable. Write once, use everywhere.

Configuration

# Start the MCP server
uvx fastskills --skills-dir /path/to/skills

# With a working directory for file output and command execution
uvx fastskills --skills-dir /path/to/skills --workdir /path/to/output

Tip: Pair FastSkills with a web search MCP server (like mcp-server-fetch) so your agent can research topics alongside executing skills. Skills handle the "how," web search handles the "what."

Contributing

Contributions welcome — new skills, core improvements, or docs:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-skill)
3. Commit your changes
4. Open a Pull Request

License

MIT License — see LICENSE for details.

Acknowledgments

• Follows the Agent Skills open standard
• Built with FastMCP
• Inspired by the skill systems in Claude Code, OpenClaw, and nanobot