zjunlp / SkillNet

Open Infrastructure for Creating, Evaluating, and Connecting AI Agent Skills Search 300,000+ community skills · One-line install · Auto-create from repos / docs / logs 5-dimension quality scoring · Semantic relationship graph Installation • Python SDK • CLI • Paper • Website • HuggingFace • Contributing • Featured By AK --- **SkillNet** is an open-source platform that treats AI agent skills as first-class, shareable packages — like npm for AI capabilities. It provides end-to-end tooling to **search**, **install**, **create**, **evaluate**, and **organize** skills, so agents can learn from the community and continuously grow. 📢 News • **🔌 [2026-03-12] SkillNet MCP Server Released!** — We've launched the Model Context Protocol (MCP) integration (maintained by CycleChain, special thanks for this great contribution!). Learn more → • **📄 [2026-03-04] SkillNet Technical Report Released!** — We've published the comprehensive SkillNet Technical Report, covering the system architecture, automated creation pipeline, multi-dimensional evaluation methodology, and the released open-source toolkits. View Report → • **🤖 [2026-02-23] OpenClaw Integration Released!** — SkillNet is now available as a built-in skill for OpenClaw. One command to install, zero config to use. The agent automatically searches, downloads, creates, evaluates, and analyzes skills on your behalf. Get started → ✨ Key Features | Feature | Description | | :-------------------------------------- | :---------------------------------------------------------------------------------------------------------------------- | | 🔍 **Search** | Find skills via keyword match or AI semantic search across 500+ curated skills | | 📦 **One‑Line Install** | — grab any skill from GitHub in seconds | | ✨ **Auto‑Create** | Convert GitHub repos, PDFs/PPTs/Word docs, conversation logs, or text prompts into structured skill packages using LLMs | | 📊 **5‑D Evaluation** | Score skills on **Safety · Completeness · Executability · Maintainability · Cost‑Awareness** | | 🕸️ **Skill Graph** | Auto-discover · · · links between skills | --- 📖 Table of Contents • Quick Start • REST API • Python SDK • CLI Reference • Configuration • Example: Scientific Discovery • OpenClaw Integration • Model Context Protocol (MCP) • Contributing • Citation --- 🚀 Quick Start **🌐 SkillNet Web** — Search, download individual skills, and explore curated skill collections through the SkillNet website. https://github.com/user-attachments/assets/9f9d35b0-36fd-4d7d-a072-39afa380b241 **🤖 OpenClaw + SkillNet** — See SkillNet in action with OpenClaw. The agent automatically searches, creates, evaluates, and analyzes skills on your behalf. Learn more → https://github.com/user-attachments/assets/9d49a00c-827d-47a4-8954-0e6b977ca547 --- 🌐 REST API The SkillNet search API is free, public, and requires no authentication. 📡 Full Parameter Reference **Endpoint:** | Parameter | Type | Default | Description | | :---------- | :----- | :--------- | :------------------------------------------------- | | | string | _required_ | Search query (keywords or natural language) | | | string | | (fuzzy match) or (semantic AI) | | | string | — | Filter: Development, AIGC, Research, Science, etc. | | | int | | Results per page (max 50) | | | int | | Page number _(keyword mode only)_ | | | int | | Minimum star count _(keyword mode only)_ | | | string | | or _(keyword mode only)_ | | | float | | Similarity threshold 0.0–1.0 _(vector mode only)_ | **Response:** --- 🐍 Python SDK Initialize Search Install Create Convert diverse sources into structured skill packages with a single call: Evaluate Score any skill across 5 quality dimensions. Accepts local paths or GitHub URLs. Analyze Relationships Map the connections between skills in a local directory — outputs , , , and edges. --- 💻 CLI Reference The CLI ships with and offers the same features with rich terminal output. | Command | Description | Example | | :--------- | :--------------------- | :--------------------------------------- | | | Find skills | | | | Install a skill | | | | Create from any source | | | | Quality report | | | | Relationship graph | | > Use for full options. Search Install Create Evaluate Analyze --- ⚙️ Configuration Environment Variables | Variable | Required For | Default | | :------------- | :--------------------------------- | :-------------------------- | | | · · | — | | | Custom LLM endpoint | | | | Private repos / higher rate limits | — | > and (public repos) work without any credentials. **Linux / macOS:** **Windows PowerShell:** --- 🔬 Example: Scientific Discovery A complete end-to-end demo showing how an AI Agent uses SkillNet to autonomously plan and execute a complex scientific workflow — from raw scRNA-seq data to a cancer target validation report. 1️⃣ Task User provides a goal: "Analyze scRNA-seq data to find cancer targets" 2️⃣ Plan Agent decomposes into: Data → Mechanism → Validation → Report 3️⃣ Discover client.search() finds cellxgene-census , kegg-database , etc. 4️⃣ Evaluate Skills are quality-gated via client.evaluate() before use 5️⃣ Execute Skills run sequentially to produce a final discovery report 👉 **Try the Interactive Demo** (Website → Scenarios → Science)  |  📓 **View Notebook** --- 🤖 OpenClaw Integration SkillNet integrates with OpenClaw as a built-in, lazy-loaded skill. Once installed, your agent automatically: • **Searches** existing skills before starting complex tasks • **Creates** new skills from repos, documents, or completed work • **Evaluates & analyzes** your local library for quality and inter-skill relationships > Community skills guide execution → successful outcomes become new skills → periodic analysis keeps the library clean. 📥 Installation **Prerequisites:** OpenClaw installed (default workspace: ) **Option A — CLI:** **Option B — Via OpenC…