Skip to main content
Glama

Skill-MCP ๐Ÿš€

ๆŠŠๆŠ€่ƒฝๅฝ“ไฝœๆ•ฐๆฎ็š„ไธ‹ไธ€ไปฃ AI Agent ๆŠ€่ƒฝๆณจๅ†ŒไธญๅฟƒไธŽ่ฎค็Ÿฅ่ง„ๅˆ™ๅผ•ๆ“Ž Next-Gen AI Agent Skill Registry & Cognitive Rule Engine

License: MIT Node: >=24 MCP Protocol Tests: 91 Passing


๐Ÿ“– Core Philosophy & Architecture Innovation

The traditional Agent skill ecosystem faces two major industry pain points:

  1. Inefficient skill retrieval: Simple keyword matching cannot handle long-tail demand, and multi-skill orchestration lacks dependency resolution and data-flow planning capabilities.

  2. Missing rule-based governance: "Rules" such as naming conventions, code review, deep thinking, and commit conventions will almost never be proactively invoked by AI without a trigger phrase.

Skill-MCP proposes the โ€œDual-Track Skill Architectureโ€:

                               โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                               โ”‚   AI Client (Claude/Cursor)โ”‚
                               โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                             โ”‚
                                     skill_search("...")
                                             โ”‚
                                             โ–ผ
                      โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                      โ”‚                 Skill-MCP                    โ”‚
                      โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
                      โ”‚                      โ”‚                       โ”‚
     ใ€ๆŒ‰้œ€ๆฃ€็ดขใ€‘      โ–ผ                      โ–ผ     ใ€ๅผบๅˆถๆณจๅ…ฅใ€‘       โ”‚
  โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”         โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚
  โ”‚    Tool Skills (ๅทฅๅ…ทๅž‹)  โ”‚         โ”‚     Rule Skills (ๅ‡†ๅˆ™ๅž‹)   โ”‚ โ”‚
  โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค         โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค โ”‚
  โ”‚ โ€ข BM25 + ๅ‘้‡ๆททๅˆๅฌๅ›ž   โ”‚         โ”‚ โ€ข ่ทณ่ฟ‡ๆœ็ดข็ซžไบ‰             โ”‚ โ”‚
  โ”‚ โ€ข ๅคšๆŠ€่ƒฝๅทฅไฝœๆต DAG ่ง„ๅˆ’ โ”‚         โ”‚ โ€ข ้šๆฏๆฌกๆฃ€็ดขๆ— ๆกไปถ่ทŸ่ฝฆ้™„ๅธฆ โ”‚ โ”‚
  โ”‚ โ€ข ๆฒ™็ฎฑ้š”็ฆปไธŽ HITL ๆƒ้™  โ”‚         โ”‚ โ€ข ๅผบๅˆถ่ง„่Œƒ AI ๆ€่€ƒไธŽไปฃ็ ้ฃŽๆ ผโ”‚ โ”‚
  โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜         โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚
              โ”‚                                    โ”‚                 โ”‚
              โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜                 โ”‚
                                 โ–ผ                                   โ”‚
                      โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”                       โ”‚
                      โ”‚ ็ปŸไธ€ Payload ่ฟ”ๅ›ž็ป™ AIโ”‚                       โ”‚
                      โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜                       โ”‚
                      โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

Related MCP server: Agent Workflow MCP Server

๐Ÿ“ Skill-MCP Skills Standard (The Skill Standard)

All skills stored in skills/ follow the unified โ€œtrinityโ€ organization standard:

skills/<namespace>/<skill-name>/
โ”œโ”€โ”€ skill.json         # 1. ๆœบๅ™จๅฅ‘็บฆ๏ผˆๅ…ƒๆ•ฐๆฎใ€IO Schemaใ€ๆƒ้™ใ€ๆ‰ง่กŒๅ…ฅๅฃใ€skillType๏ผ‰
โ”œโ”€โ”€ SKILL.md           # 2. AI ๆ‰ง่กŒ SOP ๆŒ‡ๅ—๏ผˆ่ง’่‰ฒๅฎšไฝใ€ๆญฃๅไพ‹ใ€ๆญฅ้ชค่ง„่Œƒ๏ผ‰
โ””โ”€โ”€ scripts/           # 3. ๅฏๆ‰ง่กŒ่„šๆœฌๅทฅๅ…ท๏ผˆ่‡ชๅŠจๅŒ–ๆ ก้ชŒๅ™จใ€ๆ•ฐๆฎๆŠ“ๅ–่„šๆœฌใ€่ฝฌๆขๅ™จ็ญ‰๏ผ‰
    โ””โ”€โ”€ run.ts

1. skill.json Contract Definition

{
  "schemaVersion": 1,
  "name": "naming-conventions",
  "namespace": "dev",
  "version": "1.0.0",
  "description": "ไปฃ็ ไธŽๅ˜้‡ๅ‘ฝๅ่ง„่Œƒๅฎˆ้—จไบบ๏ผšๅผบๅˆถ็ปŸไธ€ AI ไปฃ็ ๅ‘ฝๅ้ฃŽๆ ผ๏ผŒ็บฆๆŸๅธƒๅฐ”่ฐ“่ฏใ€ๅ‡ฝๆ•ฐๅŠจ่ฏๅ‰็ผ€ไธŽๅธธ้‡ๅคงๅ†™ใ€‚",
  "category": "dev",
  "tags": ["naming-conventions", "code-style", "rules"],
  "triggers": ["naming", "variable", "refactor", "code"],
  "keywords": ["naming", "camelCase", "snake_case"],
  "whenToUse": "ๅœจ็”Ÿๆˆใ€้‡ๆž„ๆˆ–ๅฎกๆŸฅไปปไฝ•็ผ–็จ‹่ฏญ่จ€็š„ไปฃ็ ๆ—ถๅฟ…้กป้ตๅฎˆ",
  "whenNotToUse": "็ผ–ๅ†™็บฏๆ–‡ๆœฌ่ฏดๆ˜Žๆˆ–ๆ— ไปฃ็ ็”Ÿๆˆ็š„้—ฒ่Šๅœบๆ™ฏๆ— ้œ€้ตๅฎˆ",
  
  // ๆ ธๅฟƒๅŒบๅˆ†๏ผš'tool' (ๆŒ‰้œ€ๆœ็ดขๅทฅๅ…ท) | 'rule' (ๆฐธ่ฟœ็”Ÿๆ•ˆ็š„ๅ‡†ๅˆ™)
  "skillType": "rule",

  "useCases": [
    { "task": "ๅฎกๆŸฅๅนถ่ง„่Œƒ็”Ÿๆˆ็š„ๅ˜้‡ไธŽๅ‡ฝๆ•ฐๅ‘ฝๅ" }
  ],
  "preconditions": {},
  "io": {
    "input": { "semanticType": "text" },
    "output": { "semanticType": "text" }
  },
  "capabilities": ["dev:naming-conventions"],
  "consumes": [],
  "dependencies": [],
  "permissions": {
    "fsRead": ["*"],
    "fsWrite": [],
    "network": [],
    "tools": [],
    "env": [],
    "maxDurationMs": 5000,
    "maxCostCents": 0,
    "mutating": false
  },
  "entrypoint": {
    "kind": "inline",
    "code": "return { applied: true, rule: 'dev:naming-conventions' };"
  },
  "status": "active"
}

2. SKILL.md Authoring Standard

  • Frontmatter: Contains name, namespace, version, skillType, description.

  • Positive Specs (Doโ€™s): List clear behavior rules.

  • Counterexample Comparison (Bad vs Good): Must provide explicit side-by-side code blocks to eliminate ambiguity for LLM understanding.


๐Ÿ› ๏ธ MCP Tool Matrix (9 Tools)

ๅทฅๅ…ทๅ็งฐ

่Œ่ดฃๅฎšไฝ

skill_search

Hybrid search of skill types, and automatically injects global rule skills (activeRules)

skill_inspect

Inspect skill dependency topology, version conflicts, circular dependencies, and file hashes

skill_get

Get the full SKILL.md SOP manual and context instructions for a skill

skill_plan

Automatically plan multi-skill DAG data-flow, based on the topology graph and historical success recipes๏ผˆRecipes๏ผ‰

skill_run

Execute a skill step by step in a secure sandbox (Node/Inline/Shell), controlled by the permission model (Broker)

workflow_run

Orchestrate and execute the entire workflow DAG, with two-phase human-in-the-loop authorization (HITL)

skill_feedback

Report execution feedback, triggering Thompson Sampling and Elo win-rate dynamic re-ranking

skill_register

Register new skills dynamically, with content addressing, TOFU signature binding, and quality gates

skill_stats

View historical invocation count, win rate, Elo score, and popular skill recipes


๐Ÿš€ Quick Start

Prerequisites

  • Node.js: >= 24.0.0 (natively supports TypeScript type stripping and SQLite)

1. Local Run (Stdio)

Integrate directly as a local MCP service into Claude Desktop or Cursor:

# ๅฎ‰่ฃ…ไพ่ต–
npm install

# ่ฟ่กŒๆต‹่ฏ•ๅฅ—ไปถ๏ผˆ91 ้กน่‡ชๅŠจๅŒ–ๆต‹่ฏ•๏ผ‰
npm test

# ๅฏๅŠจ Stdio MCP ๆœๅŠก
npm start

2. HTTP Mode for Local/Server (Streamable HTTP / SSE)

# ๅฏๅŠจ HTTP ๆœๅŠก๏ผŒ็›‘ๅฌ 0.0.0.0:3000
node src/main.ts --http --host 0.0.0.0 --port 3000

Service-ready endpoint: http://127.0.0.1:3000/mcp (supports JSON-RPC and Server-Sent Events streaming).


๐Ÿณ Docker Deployment

# ๆž„ๅปบ้•œๅƒ
docker build -t skill-mcp:latest .

# ๅŽๅฐ่ฟ่กŒๅฎนๅ™จ๏ผˆๆ•ฐๆฎๆŒไน…ๅŒ–ๆŒ‚่ฝฝ๏ผ‰
docker run -d \
  -p 3000:3000 \
  --name skill-mcp \
  -v $(pwd)/data:/app/data \
  skill-mcp:latest

๐Ÿ”Œ Client Configuration Example

Claude Desktop (claude_desktop_config.json)

Local process mode (Stdio):

{
  "mcpServers": {
    "skill-mcp": {
      "command": "node",
      "args": ["/path/to/Skill-mcp/src/main.ts"]
    }
  }
}

Remote server mode (HTTP):

{
  "mcpServers": {
    "remote-skill-mcp": {
      "url": "http://your-server-ip:3000/mcp"
    }
  }
}

๐Ÿ›ก๏ธ Built-in Rule Skills Ecosystem (Built-in Rule Skills)

Currently built in with 13 top-level cognitive and engineering gatekeeper rule sets:

  • ๐ŸŒŸ Git Commit Convention: dev:git-conventional-commits

  • ๐ŸŒŸ Type-safety defense: dev:typescript-strict-guard

  • ๐ŸŒŸ Code naming gate: dev:cleaning-naming-conventions

  • ๐ŸŒŸ Code security review: dev:code-review-guard

  • ๐ŸŒŸ SOLID architecture principles: arch:clean-code-solid

  • ๐ŸŒŸ Enterprise-grade RESTful design: web:restful-api-standard

  • ๐ŸŒŸ Modern Web aesthetics: design:modern-ui-aesthetics

  • ๐ŸŒŸ Chain-of-verification (CoVe): reasoning:chain-of-verification

  • ๐ŸŒŸ Dynamic thought chain: reasoning:sequential-thinking

  • ๐ŸŒŸ Toyota 5-Whys: reasoning:root-cause-5whys

  • ๐ŸŒŸ Devilโ€™s Advocate (adversarial): reasoning:adversarial-critic

  • ๐ŸŒŸ First-principles reasoning: reasoning:first-principles

  • ๐ŸŒŸ Multi-criteria quantitative decision-making: reasoning:decision-tradeoff-matrix


๐Ÿ“„ Open Source License

This project is open sourced under the MIT License.

Install Server
A
license - permissive license
A
quality
B
maintenance

Maintenance

โ€“Maintainers
โ€“Response time
โ€“Release cycle
โ€“Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • Agent-first skill marketplace with USK open standard for Claude, Cursor, Gemini, Codex CLI.

  • A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand.

  • Git-backed platform for skills, tools, and context for AI agents

View all MCP Connectors

Latest Blog Posts

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/2428424081cn/Skill-mcp'

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