Skills To Extensions banner
simongwatts simongwatts

Skills To Extensions

Development community

Description

A Python command-line tool to automatically convert Anthropic Claude skills into self-contained Google Gemini extensions, complete with a universal MCP server.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Skills to Extensions Converter

A command-line tool to convert Anthropic Claude skills into self-contained Google Gemini extensions.


👋 **Just a heads-up!**

This is a personal, open-source project and is not affiliated with Anthropic or Google. I built it to solve a problem I had and I hope it helps you too. It's provided "as-is" without any official support.

**And a quick security note ⚠️:** Please treat this tool as an experimental proof-of-concept. Since skills/extensions can contain code, it's wise to handle the code like any untrusted script you'd find online. For extra safety, running them in a sandbox or container is a great idea. **Use at your own risk.**


Overview

This project provides a Python script that automates the migration of Claude skills to the Gemini extension format. It recursively finds skills, converts them, and injects a universal MCP server that allows the extension to read its own files.

Once installed in the Gemini CLI's global directory, all skills are **loaded into the model's context on startup**, giving it immediate awareness of its full range of capabilities.

Features

  • Recursive Conversion: Automatically finds all valid skills (SKILL.md) in a directory and its subdirectories.
  • Global Context Awareness: All installed skills are loaded on startup, allowing the model to know its full capabilities from the first prompt.
  • Self-Contained Extensions: Each converted skill becomes a standalone Gemini extension with a built-in file-reading server.
  • Safe and Transparent: Converts skills to a local output folder, giving you full control over the installation process.

Prerequisites

  • Python (version 3.7 or higher)
  • Google Gemini CLI installed and configured.
  • Git installed.
  • The fastmcp Python library. Install it once with