发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源,助力开发者快速构建智能应用
Skill Hunter — Full Workflow
You have access to 10,000+ skills on ClawHub. This document teaches you how to find the right ones, evaluate them before installing, and manage what you've got.
Skill Hunter — Full Workflow
You have access to 10,000+ skills on ClawHub. This document teaches you how to find the right ones, evaluate them before installing, and manage what you've got.
Memory System v2.0 - Design Document
Current memory system (daily logs + MEMORY.md) lacks: - Semantic search capabilities - Structured indexing - Context-aware retrieval - Automatic consolidation
核心元数据(OpenClaw 识别的关键,必须有!)
name: document-summary slug: document-summary description: Summarizes technical documents into structured markdown. version: 1.0.2 author: kelevis
document-summary
Summarizes technical documents into structured markdown.
ZeeLin Auto-PPT — AI 精美演示文稿生成器 📊
通过 Google NotebookLM 一键生成**图文并茂、排版精美、设计震撼**的演示文稿,导出 **PDF** 到桌面。
PDF.co Routing Reference
**App name:** `pdf-co` **Base URL proxied:** `api.pdf.co`
The Graph Subgraph — Auto-Generated Query Patterns Reference
This document describes everything The Graph's graph-node auto-generates from a subgraph's `schema.graphql` file. Given a minimal entity schema, an LLM agent can use these patterns to construct any valid query without needing the full introspection result.
Runtime Data Scripts
The Rich ABIs document **interfaces** (what to call and how). Scripts provide **runtime data** (what to call it on) by importing canonical npm packages directly. No npm install required — use `bunx -p <pkg> bun script.mjs` to resolve packages at runtime.
Superfluid Protocol Skill
Complete interface documentation for Superfluid Protocol smart contracts via Rich ABI YAML references. Read `references/guides/architecture.md` for the full protocol architecture. This file maps use-cases to the right references.
Platform Compatibility Guide
This document covers which AI agent platforms support the Bitget Wallet Skill, how to install it on each, and the results of our verification testing.