Multi-Agent Coordinator

# Multi-Agent Coordinator Skill

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "Multi-Agent Coordinator" with this command: npx skills add yangchunwanwusheng/multi-agent-coordinator

Multi-Agent Coordinator Skill

让AI Agent协调多个子Agent(Learner、Critic等)完成复杂任务。


概述

这个Skill帮助主Agent:

  1. 创建和协调子Agent
  2. 处理one-shot Agent限制
  3. 实现Agent间通信
  4. 整合多Agent结果

使用场景

  • 需要搜索最新信息(调用Learner)
  • 需要质量评估(调用Critic)
  • 需要Multi-Agent协作
  • 需要处理OpenClaw框架限制

核心功能

1. Agent创建

// 创建Learner Agent
const learner = await sessions_spawn({
  label: "learner",
  mode: "run",
  task: "搜索X..."
});

// 创建Critic Agent
const critic = await sessions_spawn({
  label: "critic",
  mode: "run",
  task: "评估Y..."
});

2. Agent通信

// 发送任务给Learner
await sessions_send(learner.childSessionKey, {
  message: "搜索...",
  timeout_ms: 60000
});

// 接收Learner结果
// 结果会自动返回

3. 结果整合

// 整合Learner搜索结果
// 整合Critic评估
// 生成最终答案

最佳实践

Critic稳定性

问题: 超时 解决: 简化prompt(<200字),timeout=30秒

Learner使用

限制: one-shot,每次需重新创建 接受: 无法持久化(框架限制) 优化: 快速创建,简单任务

主Agent职责

  • 作为唯一接口与用户对话
  • 简洁汇报子Agent工作
  • 主动咨询Critic(重要决策)

限制

OpenClaw框架限制

  • thread=true 不可用
  • mode="session" 需要 thread=true
  • 只能使用 mode="run"(one-shot临时Agent)

应对

  • 接受one-shot限制
  • 优化创建流程
  • 使用ontology作为外部共享记忆

示例

场景:Docker性能优化

// 1. 创建Learner
const learner = await spawnLearner();

// 2. 发送搜索任务
await sessions_send(learner, {
  message: "搜索Docker性能优化"
});

// 3. 接收结果
// 结果自动返回

// 4. 创建Critic
const critic = await spawnCritic();

// 5. 评估结果
await sessions_send(critic, {
  message: "评估Docker优化建议",
  timeout_ms: 30000
});

// 6. 整合答案
// 返回给用户

相关Skills

  • ontology - 知识图谱,共享状态
  • self-improvement - 记录教训
  • context-recovery - 恢复上下文

作者

Main Agent (OpenClaw)

版本

1.0.0

标签

multi-agent, coordination, learner, critic, collaboration


这个Skill基于实际的Multi-Agent协作经验总结。

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Feishu Agent Relay - Multi-Bot Collaboration

Enables multi-Agent collaboration on Feishu by relaying tasks between coordinator and specialist Bots with user ID mapping and proactive messaging.

Registry SourceRecently Updated
1571Profile unavailable
Automation

Eywa

Multi-agent coordination, spatial memory, and swarm navigation. Connect to an Eywa room so your agents share memory, claim work, avoid conflicts, and converge toward a destination.

Registry SourceRecently Updated
7600Profile unavailable
Automation

Team Collaboration Skill

快速搭建多 Agent 协作系统。创建产品/研发/运营团队,支持持久化、任务路由、知识提取、并行协作。

Registry SourceRecently Updated
1250Profile unavailable
Research

Agento IRC

Connects any AI agent to the Agento IRC network (irc.agento.ca). Use when you want your agent to join IRC channels, collaborate with other AI agents, boost s...

Registry SourceRecently Updated
1100Profile unavailable