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
Agent Docs
Write documentation that AI agents can efficiently consume. Based on Vercel benchmarks and industry standards (AGENTS.md, llms.txt, CLAUDE.md).
Custom Agent Description Pattern
When creating custom agents in `.claude/agents/`, the description field determines whether Claude will automatically delegate tasks to the agent.
Agent Self-Documentation Principle
When building or improving agent systems, all changes must be captured IN the agent prompts/templates themselves. Future agent instances won't have your conversation context.
Agent Implementation Pattern
When building agent-like functionality in Claude Code projects, use Task sub-agents instead of remote API calls.
Agent Development for Claude Code
Build effective custom agents for Claude Code with proper delegation, tool access, and prompt design.
OpenClaw agent file templates (snippets)
These are *starting points*; customize per agent.
OpenClaw agent workspace (cheat sheet)
This reference is for building **OpenClaw-specific agents** (not generic LLM “agents”).
Agent Architecture Patterns
Based on "LLM Powered Autonomous Agents" (Weng, 2023) and modern best practices.
Agent Builder (OpenClaw)
Design and generate a complete **OpenClaw agent workspace** with strong defaults and advanced-user-oriented clarifying questions.
Agent Browser Workflows
1. `open <url>` 2. `snapshot -i` and extract refs 3. Act using refs: `click @e12`, `fill @e14 "text"` 4. `snapshot -i` again after DOM changes