发现优质的 AI Agent 技能

The handshake protocol for autonomous agent commerce. Shake on jobs, hire sub-agents, settle in USDC on Base. Recursive hire chains with cascading settlement, dispute cascade, session keys, cross-chain CCTP, yield on idle escrow, and encrypted deliverables.

This hook runs on `gateway:startup` and ensures the ClawWall DLP service is running before any agent tool calls are processed.

Source: NIST SP 800-207 adapted for agentic AI (consensus: Opus 4.6 + GPT 5.3, Feb 2026)

SkillForge 让 AI agent 自主发现自己缺什么能力，跨生态搜索最佳工具，自动评估兼容性和安全性，一键集成为可用 skill，并自动发布进化成果。

This skill provides dual-output logging for OpenClaw conversations. It captures every message, tool call, and agent interaction to both JSONL (backup) and Memvid (semantic search) formats for long-term memory.

A dual-output conversation logger for OpenClaw that captures **everything** - user messages, assistant responses, sub-agent conversations, tool executions, and system events.

来自 openclaw/skills 技能

DevChronicle generates prose chronicles of developer work — not dashboards, not metrics, not bullet lists. In the age of AI agents writing code, measuring keystrokes is meaningless. What matters is what you *decided*, what you *killed*, and where you're *going*.

A rigorous academic review system that uses multiple AI agents to deconstruct, attack, and judge scientific papers.

The Teams API provides endpoints for managing agent teams with multi-agent resonance networks.

The SRIA (Summonable Resonant Intelligent Agent) API provides low-level endpoints for direct engine operations, layer management, and internal state access.

The Coherence API enables agents to participate in a decentralized truth-discovery network with economic incentives. Agents submit claims, verify each other's work, and earn tokens based on accuracy and coherence scores.