Skrills
Coordinate skills between Codex, Copilot, and Claude Code. Validates, analyzes, and syncs skills, subagents, commands, and configuration between multiple CLIs.
What is Skrills?
Skrills is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to coordinate skills between codex, copilot, and claude code. validates, analyzes, and syncs skills, subagents, commands, and configuration between multiple clis.
Coordinate skills between Codex, Copilot, and Claude Code. Validates, analyzes, and syncs skills, subagents, commands, and configuration between multiple CLIs.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Coordinate skills between Codex, Copilot, and Claude Code. V
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx skrillsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Skrills
Skrills is a Rust-based MCP server and CLI tool that synchronizes, validates, and analyzes AI coding skills across multiple CLI environments — Claude Code, OpenAI Codex CLI, GitHub Copilot CLI, and Cursor. It exposes a 36-tool MCP interface covering multi-directional skill sync, dependency resolution with cycle detection, token analytics, session mining from conversation history, and a terminal UI for managing your AI skill library. Teams that use more than one AI coding assistant use Skrills to keep their custom commands, subagents, and configuration consistent across all tools from a single source of truth.
Prerequisites
- At least one supported AI CLI installed: Claude Code, OpenAI Codex CLI, GitHub Copilot CLI, or Cursor
- Stable Rust toolchain (if building from source via cargo install skrills)
- Optional: ANTHROPIC_API_KEY or OPENAI_API_KEY for AI-powered skill generation features
- An MCP-compatible client to connect to the skrills MCP server
- curl or PowerShell (for the one-line installer scripts)
Install Skrills
Use the one-line installer for your platform, or install via Cargo if you have Rust available.
# macOS/Linux:
curl -LsSf https://raw.githubusercontent.com/athola/skrills/HEAD/scripts/install.sh | sh
# Windows PowerShell:
powershell -ExecutionPolicy Bypass -NoLogo -NoProfile -Command "Remove-Item alias:curl -ErrorAction SilentlyContinue; iwr https://raw.githubusercontent.com/athola/skrills/HEAD/scripts/install.ps1 -UseBasicParsing | iex"
# Via Cargo:
cargo install skrillsValidate your existing skill configurations
Run the validate command to check your current skill files across all installed CLIs for errors, conflicts, and missing dependencies. The --autofix flag applies safe automatic corrections.
skrills validate --target both --autofixSync skills across all CLIs
Push your canonical skill definitions to all configured CLI environments in one command.
skrills sync-allStart the MCP server
Launch the Skrills MCP server so your AI client can access all 36 tools. The --http flag starts an HTTP endpoint; omit it for stdio mode.
skrills serve --http 127.0.0.1:3000 --openConfigure your MCP client
Add Skrills to your MCP client configuration. For stdio mode (Claude Desktop), use npx skrills as the command.
{
"mcpServers": {
"skrills": {
"command": "npx",
"args": ["skrills"]
}
}
}Analyze token usage and get optimization suggestions
Run the analyzer to identify high-token skills and get recommendations for improving efficiency across your skill library.
skrills analyze --min-tokens 1000 --suggestionsSkrills Examples
Client configuration
Claude Desktop config running Skrills as a local MCP server via npx.
{
"mcpServers": {
"skrills": {
"command": "npx",
"args": ["skrills"]
}
}
}Prompts to try
Example requests once Skrills is connected as an MCP server.
- "Validate all my skills across Claude Code and Codex CLI and fix any issues"
- "Sync my skills so Claude Code and Copilot have the same definitions"
- "Which of my skills use the most tokens? Give me optimization suggestions"
- "Show me my session mining results from Claude Code conversation history"
- "List all subagents defined in my Codex CLI config"Troubleshooting Skrills
skrills command not found after installation
Ensure the installer's target binary directory is in your PATH. On macOS/Linux this is typically ~/.local/bin or ~/.cargo/bin. Run 'source ~/.bashrc' or start a new shell after installation.
Skill generation features fail or produce errors
Skill generation requires either ANTHROPIC_API_KEY or OPENAI_API_KEY to be set in your environment. Export the appropriate key and retry: export ANTHROPIC_API_KEY=your-key
Sync-all reports conflicts between CLI skill definitions
Run 'skrills validate --target both' first to see the full conflict report. Skrills performs dependency resolution with cycle detection — resolve circular references manually before re-running sync-all.
Frequently Asked Questions about Skrills
What is Skrills?
Skrills is a Model Context Protocol (MCP) server that coordinate skills between codex, copilot, and claude code. validates, analyzes, and syncs skills, subagents, commands, and configuration between multiple clis. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Skrills?
Follow the installation instructions on the Skrills GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Skrills?
Skrills works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Skrills free to use?
Yes, Skrills is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Skrills Alternatives — Similar Developer Tools Servers
Looking for alternatives to Skrills? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Skrills in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Skrills?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.