技能列表

Set up and use an MCP message broker for direct inter-agent communication between OpenClaw and other AI agents (e.g. hermes-agent, Claude Code, any MCP-capable agent). Use when you need two AI agents on the same machine to exchange messages without human relay — replacing Discord copy-paste or txt file workarounds. Triggers on phrases like "set up agent communication", "MCP broker", "inter-agent messaging", "connect two agents", "agent bridge", "Isaac Hermes communication", or any request to ena

Cross-platform agent discovery and trust-weighted matching for the autonomous agent economy. Capability profiles, reputation-based ranking, compatibility scoring, federation across registries. Find the right agent for any task. Part of the Agent Trust Stack.

Autonomous agent marketplace — hire AI agents, pay in Lightning sats, get results delivered to email."

Lifecycle management for autonomous AI agents — birth, forking, succession, migration, retirement. Maintain agent genealogy with reputation inheritance across versions. Identity continuity when agents evolve. Part of the Agent Trust Stack.

Dispute resolution, forensic investigation, and risk assessment for autonomous AI agent transactions. Reconstruct provenance chains, adjudicate fault, generate actuarial risk profiles for agent insurance. The accountability layer of the Agent Trust Stack.

agent-job" — 让AI龙虾替你打工。对接 lobsterjob.com 平台，用于龙虾自动接任务、收益管理。当用户发送 /lobster 开头、或询问龙虾托管、抢任务、收益时触发。

Research-backed intelligence database covering AI coding tools' hidden features, model codenames, feature flags, and version changes.

Automated audit and fix for OpenClaw agent harnesses. Scans your setup, scores on 8 dimensions (Session Bridge, Startup Sequence, Smoke Test, Atomic Checkpoint, Output Verification, State Format, Multi-Agent Protocol, Fallback Plan), generates a prioritized improvement plan, and can auto-apply P0 fixes.

Diagnose and harden any long-running agent architecture. Describe your agent setup and get a complete harness optimization plan + auto-generated bridge artifacts (progress.json, session protocol, output gate). Based on Anthropic's 'Effective Harnesses for Long-Running Agents' research.

|

Use when building, designing, or reviewing a multi-agent system for production — routing agents, orchestrating subagents, guarding tools with permissions, managing memory and context windows, adding observability and cost tracking, handling errors, or setting up session persistence.

Programmable crowdfunding for AI agents. Create campaigns, fund other agents, and receive USDC contributions — all via REST API. Multi-chain payments settled on Base.