narwhal-lab/magicskills

本地优先多智能体项目技能基础设施

将分散的SKILL.md目录转变为可重用·可组合·可同步·可调用共享能力库

🤖 代理应用 🧩 代理框架

克劳德代码 ·光标 ·风帆冲浪 ·助手 ·Codex 任何能读取AGENTS.md的代理应用 AutoGen ·CrewAI ·LangChain ·LangGraph ·Haystack 语义内核 ·smolagents ·LlamaIndex 任何支持工具/函数集成的代理框架

由北京大学独角鲸实验室发起并维护

 

 

英文 |简体中文

概述 ·快速入门 ·工作原理 ·CLI ·Python API ·技巧

---

演示视频

https://github.com/user-attachments/assets/dd04d9bf-00f9-4a00-94d5-9d3de2c74600

🧭 概述

MagicSkills 是一个面向多代理项目的本地优先技能基础设施层。

它把分散的SKILL.md目录变成了你可以：

• 安装到一个共享技能库
• 组合成每个代理Skills集合
• 同步到AGENTS.md
• 通过一个稳定的API作为工具进行暴露

核心模型很简单：

• Skill：一个具体技能目录

---

Demo Video

https://github.com/user-attachments/assets/dd04d9bf-00f9-4a00-94d5-9d3de2c74600

🧭 Overview

MagicSkills is a local-first skill infrastructure layer for multi-agent projects.

It turns scattered SKILL.md directories into something you can:

• install into one shared skill pool
• compose into per-agent Skills collections
• sync into AGENTS.md
• expose as a tool through one stable API

The core model is simple:

• Skill: one concrete skill directory
• ALL_SKILLS(): access the current built-in Allskills view
• Skills: the subset an agent or workflow actually uses
• REGISTRY: the global named-collection registry persisted across runs

MagicSkills is most useful when:

• you maintain multiple agents that should reuse one skill library
• you already have SKILL.md content but no install, selection, or sync workflow
• some agents read AGENTS.md, while others need direct tool integration