Skill-MCP
This server is a skill-management MCP endpoint that gives AI agents discoverable, retrievable, executable, and evaluable reusable skills/workflows.
Search skills by task intent –
skill_searchperforms hybrid retrieval (BM25 + vector + RRF), returns ranked candidates with fit reasons, and cleanly rejects out-of-domain queries.Inspect skill metadata –
skill_inspectshows manifests, dependency trees, and permissions without loading full content.Fetch full skill packages –
skill_getreturns the complete SKILL.md, manifest, file list, and parsed dependencies.Plan multi-step work –
skill_plandecomposes a task into a workflow DAG of skill combinations, using capability graph search when no LLM is available.Execute a single skill –
skill_runruns skills in a permission sandbox, with two-phase human-in-the-loop approval when needed.Run complete workflows –
workflow_runexecutes planned DAGs with topological data flow, retries, checkpoints, and whole-chain authorization.Give feedback and improve ranking –
skill_feedbackreports outcomes/ratings to drive bandit/Elo learning and alternative retrieval.Register or upgrade skills –
skill_registeradds new skills (append-only), optionally requiring Ed25519 signatures and sandbox-tested upgrades.Monitor skill quality –
skill_statssurfaces success rate, Elo, quality score, latency/cost, and discovered workflow recipes.
Click on "Deploy 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-MCP Search 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 🚀
把技能当作数据的下一代 AI Agent 技能注册中心与认知规则引擎 Next-Gen AI Agent Skill Registry & Cognitive Rule Engine
📖 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 “Dual-Track Skill Architecture”:
┌───────────────────────────┐
│ AI Client (Claude/Cursor)│
└─────────────┬─────────────┘
│
skill_search("...")
│
▼
┌──────────────────────────────────────────────┐
│ Skill-MCP │
├──────────────────────┬───────────────────────┤
│ │ │
【按需检索】 ▼ ▼ 【强制注入】 │
┌─────────────────────────┐ ┌────────────────────────────┐ │
│ Tool Skills (工具型) │ │ Rule Skills (准则型) │ │
├─────────────────────────┤ ├────────────────────────────┤ │
│ • BM25 + 向量混合召回 │ │ • 跳过搜索竞争 │ │
│ • 多技能工作流 DAG 规划 │ │ • 随每次检索无条件跟车附带 │ │
│ • 沙箱隔离与 HITL 权限 │ │ • 强制规范 AI 思考与代码风格│ │
└───────────┬─────────────┘ └────────────┬───────────────┘ │
│ │ │
└──────────────────┬─────────────────┘ │
▼ │
┌──────────────────────┐ │
│ 统一 Payload 返回给 AI│ │
└──────────────────────┘ │
└──────────────────────────────────────────────┘Related MCP server: craft
📐 Skill-MCP Skills Standard (The Skill Standard)
All skills stored in skills/ follow the unified “trinity” organization standard:
skills/<namespace>/<skill-name>/
├── skill.json # 1. 机器契约(元数据、IO Schema、权限、执行入口、skillType)
├── SKILL.md # 2. AI 执行 SOP 指南(角色定位、正反例、步骤规范)
└── scripts/ # 3. 可执行脚本工具(自动化校验器、数据抓取脚本、转换器等)
└── run.ts1. skill.json Contract Definition
{
"schemaVersion": 1,
"name": "naming-conventions",
"namespace": "dev",
"version": "1.0.0",
"description": "代码与变量命名规范守门人:强制统一 AI 代码命名风格,约束布尔谓词、函数动词前缀与常量大写。",
"category": "dev",
"tags": ["naming-conventions", "code-style", "rules"],
"triggers": ["naming", "variable", "refactor", "code"],
"keywords": ["naming", "camelCase", "snake_case"],
"whenToUse": "在生成、重构或审查任何编程语言的代码时必须遵守",
"whenNotToUse": "编写纯文本说明或无代码生成的闲聊场景无需遵守",
// 核心区分:'tool' (按需搜索工具) | 'rule' (永远生效的准则)
"skillType": "rule",
"useCases": [
{ "task": "审查并规范生成的变量与函数命名" }
],
"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 (Do’s): List clear behavior rules.
Counterexample Comparison (Bad vs Good): Must provide explicit side-by-side code blocks to eliminate ambiguity for LLM understanding.
🛠️ MCP Tool Matrix (9 Tools)
工具名称 | 职责定位 |
| 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(Recipes) |
| 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 |
🚀 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:
# 安装依赖
npm install
# 运行测试套件(91 项自动化测试)
npm test
# 启动 Stdio MCP 服务
npm start2. HTTP Mode for Local/Server (Streamable HTTP / SSE)
# 启动 HTTP 服务,监听 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).
🐳 Docker Deployment
# 构建镜像
docker build -t skill-mcp:latest .
# 后台运行容器(数据持久化挂载)
docker run -d \
-p 3000:3000 \
--name skill-mcp \
-v $(pwd)/data:/app/data \
skill-mcp:latest🔌 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"
}
}
}🛡️ Built-in Rule Skills Ecosystem (Built-in Rule Skills)
Currently built in with 13 top-level cognitive and engineering gatekeeper rule sets:
🌟 Git Commit Convention:
dev:git-conventional-commits🌟 Type-safety defense:
dev:typescript-strict-guard🌟 Code naming gate:
dev:cleaning-naming-conventions🌟 Code security review:
dev:code-review-guard🌟 SOLID architecture principles:
arch:clean-code-solid🌟 Enterprise-grade RESTful design:
web:restful-api-standard🌟 Modern Web aesthetics:
design:modern-ui-aesthetics🌟 Chain-of-verification (CoVe):
reasoning:chain-of-verification🌟 Dynamic thought chain:
reasoning:sequential-thinking🌟 Toyota 5-Whys:
reasoning:root-cause-5whys🌟 Devil’s Advocate (adversarial):
reasoning:adversarial-critic🌟 First-principles reasoning:
reasoning:first-principles🌟 Multi-criteria quantitative decision-making:
reasoning:decision-tradeoff-matrix
📄 Open Source License
This project is open sourced under the MIT License.
Available Tools
9 toolsskill_feedbackA
报告执行结果与评分,驱动 bandit/Elo 排名与备选检索(学习闭环;会覆盖同一次 skill_run 的自动记账,不重复计数)。
Inputs: skill (required), outcome (required), task, runId, +5 more.
skill_getC
获取 skill 的完整包:manifest + SKILL.md 正文 + 文件清单 + 已解析依赖(渐进披露的正文环节)。
Inputs: key, name.
skill_inspectC
查看 skill 的 manifest、依赖树与权限清单(不含正文,成本低)。
Inputs: key, name.
skill_planC
把任务规划成 skill 组合的 workflow DAG(分解-检索-组合;无 LLM 时用能力闭包图搜索)。
Inputs: task (required), context.
skill_registerA
注册或升级 skill(append-only;v3:trust 模式需 Ed25519 签名,gate 模式下升级需自带 tests 过沙箱)。
Inputs: manifest (required), files, signature, publisherKey.
skill_runA
在权限沙箱中执行单个 skill。权限不足时返回 requiresApproval(两段式 HITL,approveAsks: true 授权后重试)。
Inputs: skill (required), task, inputs, timeoutMs, +2 more.
skill_searchA
按任务检索 skill:混合检索(BM25 + 向量 + RRF)+ 五维任务适配打分,返回带理由的候选列表。先做这个再动手。
Inputs: query (required), topK, context, filters.
skill_statsA
查看 skill 的评价指标:成功率(Wilson)、Elo、质量分、延迟成本,以及挖掘出的 workflow recipe。
Inputs: key.
workflow_runB
执行 skill_plan 产出的 DAG:拓扑序数据流、重试、检查点、整链授权。
Inputs: dag (required), task, inputs, approveAsks, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
每个工具对应一个明确的职责阶段:搜索、查看元信息、获取全文、规划、执行单技能、执行工作流、反馈、注册、查看统计,彼此边界清晰。workflow_run 与 skill_run 通过单个体与 DAG 执行明确区分,不易产生误选。
大多数工具遵循 skill_<action> 的模式,如 skill_search、skill_inspect、skill_register,具有较高的可预测性。但 workflow_run 没有使用 skill_ 前缀,且 skill_stats、skill_feedback 以名词而非动词结尾,存在少量风格不一致。
9 个工具覆盖了从发现、规划、执行到反馈、学习、注册、查询的完整闭环,每个工具都有独立且必要的职责。数量处于合理区间,没有冗余或缺失。
工具面覆盖了 skill 的生命周期:注册/升级、检索、检查、获取、单技能执行、工作流执行、反馈学习、统计评估。缺少删除/下架属于 append-only 设计下的有意限制,不构成明显缺口。
Maintenance
Related MCP Connectors
One place to build, share, and govern the skills and tools your AI agents use at work.
Governed AI agent skills — one library, distributed to devs and exposed to remote agents over MCP.
AI agent marketplace for automated employees, workflows, skills, and tool orchestration.
Shared business knowledge, tools and skills for AI agents, with citations and approval controls.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceEnables 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
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to index and search local skill libraries, persist and resume task checkpoints, and run validated workflow plans with controlled approval and write permissions.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to dynamically retrieve and use authorized skills through the Model Context Protocol, with API key authentication, permission-based access control, REST administration, and audit logging.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search, retrieve, score, compose, and verify reusable agent skills from the SkillForge registry via MCP.21 npmMIT