An MCP server that brings Claude's Skills pattern to any MCP-compatible agent, letting you create modular, reusable skills once and deploy them across Claude, Cursor, VS Code, and more.
git clone https://github.com/skills-mcp/skills-mcp.gitSkills MCP is an MCP server inspired by Claude's Skills format that lets you define modular, reusable skills in a directory and expose them automatically to any MCP-compatible agent. By pointing the server at a skills folder, agents like Claude Code, Claude for Desktop, Cursor, and VS Code can discover and use those skills without redundant configuration. The core value proposition is write-once, use-everywhere: a single skills directory works across all supported tools. Setup is handled via npx with no global install required, and configuration is done through each tool's standard MCP JSON config file. This approach helps developers and teams maintain consistent agent behavior and domain expertise across multiple AI coding environments.
Run the server via npx by adding a skills-mcp entry to your agent's MCP config file (e.g., .mcp.json for Claude Code, .cursor/mcp.json for Cursor, or .vscode/mcp.json for VS Code). Pass the absolute path to your skills directory using the -s flag as a command argument. Once configured, restart your agent and it will automatically discover the skills in the specified directory.
Sharing a library of custom agent skills across Claude Code, Cursor, and VS Code without duplication
Giving an AI agent domain-specific expertise by pointing it at a curated skills directory
Standardizing agent behavior across a development team using a shared skills folder
Quickly bootstrapping MCP skill support in a new project using a single npx command
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/skills-mcp/skills-mcpCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Act as an MCP-compatible agent with the following skills: [SKILL1], [SKILL2], [SKILL3]. Use these skills to accomplish [TASK] for [COMPANY] in the [INDUSTRY] sector. Provide a step-by-step plan and execute each step using the specified skills.
# Task Execution Plan for GreenTech Solutions ## Task: Optimize Supply Chain Operations ### Step 1: Data Collection - **Skill Used:** Data Extraction - **Action:** Gather supply chain data from ERP systems and IoT sensors. - **Output:** Extracted data from GreenTech's ERP and sensor networks. ### Step 2: Data Analysis - **Skill Used:** Data Analysis - **Action:** Analyze the collected data to identify inefficiencies. - **Output:** Identified bottlenecks in the logistics process. ### Step 3: Optimization Recommendations - **Skill Used:** Recommendation Engine - **Action:** Provide actionable recommendations to optimize the supply chain. - **Output:** Recommendations include rerouting shipments and adjusting inventory levels. ### Step 4: Implementation Plan - **Skill Used:** Task Automation - **Action:** Create a detailed implementation plan for the recommended changes. - **Output:** Implementation plan with timelines and responsible teams.
AI assistant built for thoughtful, nuanced conversation
IronCalc is a spreadsheet engine and ecosystem
ITIL-aligned IT service management platform
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan