发现优质的 AI Agent 技能

Only available when the IDE is **Cursor** (not VS Code).

Two ways to use Cursor Agent from OpenClaw, for different scenarios.

Use this reference when selecting routing strategy for a new OpenClaw agent.

Use this skill to create one new OpenClaw agent and finish routing/config updates in one pass.

**ZH-CN:** 本技能允许 Agent 直接调用 MemOS 云平台 API，实现记忆的检索、添加、删除以及反馈功能。 **EN-US:** This skill allows the Agent to interact with MemOS Cloud APIs for memory search, addition, deletion, and feedback.

来自 openclaw/skills 技能

来自 openclaw/skills 技能

This skill transforms the agent into a Roleplay Game Master (GM) or Character with long-term memory.

OpenClaw agent skill for OKX exchange REST API v5 and WebSocket — market data, account management, and order trading

Execute comprehensive financial research queries using CueCue's AI-powered multi-agent system. This TypeScript SDK provides modern async/await patterns, full type safety, and both CLI and programmatic interfaces.

Overreach is the most common cause of systemic failure in both humans and AI agents. It occurs when your **Error Creation Rate** exceeds your **Error Correction Capacity**.

Errors are inevitable; their correction is not. This protocol provides a systematic way for an AI agent to handle failures and prevent their recurrence.