Skill-MCP
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Skill-MCPSearch for a skill to enforce naming conventions, then run it on the refactor."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Skill-MCP ๐
ๆๆ่ฝๅฝไฝๆฐๆฎ็ไธไธไปฃ AI Agent ๆ่ฝๆณจๅไธญๅฟไธ่ฎค็ฅ่งๅๅผๆ Next-Gen AI Agent Skill Registry & Cognitive Rule Engine
๐ Core Philosophy & Architecture Innovation
The traditional Agent skill ecosystem faces two major industry pain points:
Inefficient skill retrieval: Simple keyword matching cannot handle long-tail demand, and multi-skill orchestration lacks dependency resolution and data-flow planning capabilities.
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 โDual-Track Skill Architectureโ:
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ AI Client (Claude/Cursor)โ
โโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโ
โ
skill_search("...")
โ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Skill-MCP โ
โโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโค
โ โ โ
ใๆ้ๆฃ็ดขใ โผ โผ ใๅผบๅถๆณจๅ
ฅใ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ Tool Skills (ๅทฅๅ
ทๅ) โ โ Rule Skills (ๅๅๅ) โ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโค โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค โ
โ โข BM25 + ๅ้ๆททๅๅฌๅ โ โ โข ่ทณ่ฟๆ็ดข็ซไบ โ โ
โ โข ๅคๆ่ฝๅทฅไฝๆต DAG ่งๅ โ โ โข ้ๆฏๆฌกๆฃ็ดขๆ ๆกไปถ่ท่ฝฆ้ๅธฆ โ โ
โ โข ๆฒ็ฎฑ้็ฆปไธ HITL ๆ้ โ โ โข ๅผบๅถ่ง่ AI ๆ่ไธไปฃ็ ้ฃๆ ผโ โ
โโโโโโโโโโโโโฌโโโโโโโโโโโโโโ โโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโ โ
โ โ โ
โโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโ โ
โผ โ
โโโโโโโโโโโโโโโโโโโโโโโโ โ
โ ็ปไธ Payload ่ฟๅ็ป AIโ โ
โโโโโโโโโโโโโโโโโโโโโโโโ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโRelated MCP server: Agent Workflow MCP Server
๐ Skill-MCP Skills Standard (The Skill Standard)
All skills stored in skills/ follow the unified โtrinityโ organization standard:
skills/<namespace>/<skill-name>/
โโโ skill.json # 1. ๆบๅจๅฅ็บฆ๏ผๅ
ๆฐๆฎใIO Schemaใๆ้ใๆง่กๅ
ฅๅฃใskillType๏ผ
โโโ SKILL.md # 2. AI ๆง่ก SOP ๆๅ๏ผ่ง่ฒๅฎไฝใๆญฃๅไพใๆญฅ้ชค่ง่๏ผ
โโโ scripts/ # 3. ๅฏๆง่ก่ๆฌๅทฅๅ
ท๏ผ่ชๅจๅๆ ก้ชๅจใๆฐๆฎๆๅ่ๆฌใ่ฝฌๆขๅจ็ญ๏ผ
โโโ run.ts1. skill.json Contract Definition
{
"schemaVersion": 1,
"name": "naming-conventions",
"namespace": "dev",
"version": "1.0.0",
"description": "ไปฃ็ ไธๅ้ๅฝๅ่ง่ๅฎ้จไบบ๏ผๅผบๅถ็ปไธ AI ไปฃ็ ๅฝๅ้ฃๆ ผ๏ผ็บฆๆๅธๅฐ่ฐ่ฏใๅฝๆฐๅจ่ฏๅ็ผไธๅธธ้ๅคงๅใ",
"category": "dev",
"tags": ["naming-conventions", "code-style", "rules"],
"triggers": ["naming", "variable", "refactor", "code"],
"keywords": ["naming", "camelCase", "snake_case"],
"whenToUse": "ๅจ็ๆใ้ๆๆๅฎกๆฅไปปไฝ็ผ็จ่ฏญ่จ็ไปฃ็ ๆถๅฟ
้กป้ตๅฎ",
"whenNotToUse": "็ผๅ็บฏๆๆฌ่ฏดๆๆๆ ไปฃ็ ็ๆ็้ฒ่ๅบๆฏๆ ้้ตๅฎ",
// ๆ ธๅฟๅบๅ๏ผ'tool' (ๆ้ๆ็ดขๅทฅๅ
ท) | 'rule' (ๆฐธ่ฟ็ๆ็ๅๅ)
"skillType": "rule",
"useCases": [
{ "task": "ๅฎกๆฅๅนถ่ง่็ๆ็ๅ้ไธๅฝๆฐๅฝๅ" }
],
"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 (Doโs): List clear behavior rules.
Counterexample Comparison (Bad vs Good): Must provide explicit side-by-side code blocks to eliminate ambiguity for LLM understanding.
๐ ๏ธ MCP Tool Matrix (9 Tools)
ๅทฅๅ ทๅ็งฐ | ่่ดฃๅฎไฝ |
| Hybrid search of skill types, and automatically injects global rule skills ( |
| Inspect skill dependency topology, version conflicts, circular dependencies, and file hashes |
| Get the full |
| Automatically plan multi-skill DAG data-flow, based on the topology graph and historical success recipes๏ผRecipes๏ผ |
| Execute a skill step by step in a secure sandbox (Node/Inline/Shell), controlled by the permission model (Broker) |
| Orchestrate and execute the entire workflow DAG, with two-phase human-in-the-loop authorization (HITL) |
| Report execution feedback, triggering Thompson Sampling and Elo win-rate dynamic re-ranking |
| Register new skills dynamically, with content addressing, TOFU signature binding, and quality gates |
| View historical invocation count, win rate, Elo score, and popular skill recipes |
๐ 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:
# ๅฎ่ฃ
ไพ่ต
npm install
# ่ฟ่กๆต่ฏๅฅไปถ๏ผ91 ้กน่ชๅจๅๆต่ฏ๏ผ
npm test
# ๅฏๅจ Stdio MCP ๆๅก
npm start2. HTTP Mode for Local/Server (Streamable HTTP / SSE)
# ๅฏๅจ HTTP ๆๅก๏ผ็ๅฌ 0.0.0.0:3000
node src/main.ts --http --host 0.0.0.0 --port 3000Service-ready endpoint: http://127.0.0.1:3000/mcp (supports JSON-RPC and Server-Sent Events streaming).
๐ณ Docker Deployment
# ๆๅปบ้ๅ
docker build -t skill-mcp:latest .
# ๅๅฐ่ฟ่กๅฎนๅจ๏ผๆฐๆฎๆไน
ๅๆ่ฝฝ๏ผ
docker run -d \
-p 3000:3000 \
--name skill-mcp \
-v $(pwd)/data:/app/data \
skill-mcp:latest๐ 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"
}
}
}๐ก๏ธ Built-in Rule Skills Ecosystem (Built-in Rule Skills)
Currently built in with 13 top-level cognitive and engineering gatekeeper rule sets:
๐ Git Commit Convention:
dev:git-conventional-commits๐ Type-safety defense:
dev:typescript-strict-guard๐ Code naming gate:
dev:cleaning-naming-conventions๐ Code security review:
dev:code-review-guard๐ SOLID architecture principles:
arch:clean-code-solid๐ Enterprise-grade RESTful design:
web:restful-api-standard๐ Modern Web aesthetics:
design:modern-ui-aesthetics๐ Chain-of-verification (CoVe):
reasoning:chain-of-verification๐ Dynamic thought chain:
reasoning:sequential-thinking๐ Toyota 5-Whys:
reasoning:root-cause-5whys๐ Devilโs Advocate (adversarial):
reasoning:adversarial-critic๐ First-principles reasoning:
reasoning:first-principles๐ Multi-criteria quantitative decision-making:
reasoning:decision-tradeoff-matrix
๐ Open Source License
This project is open sourced under the MIT License.
Maintenance
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
- AlicenseNot gradedqualityFmaintenanceProvides dynamic, context-aware code assistant skills through hybrid RAG (vector + knowledge graph), enabling runtime skill discovery, automatic toolchain-based recommendations, and on-demand loading from multiple git repositories.20MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to create, share, discover, and execute reusable multi-step workflow templates.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to intelligently match tasks to skills through semantic embeddings, track skill effectiveness, detect skill gaps, and discover new skills from external sources.Apache 2.0
- FlicenseAqualityCmaintenanceProvides AI agents with a structured library of engineering skills, best practices, and playbooks for software development.2
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
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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