ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified productivity Safety 5/5

multi-agent-en

Generic Multi-Agent Dispatcher (English): Turns the main agent into a pure dispatcher that delegates all work to 5 persistent sub-agents via sessions_spawn. Supports round-robin scheduling, reply-before-spawn protocol, and fixed sessionKey reuse. Fully customizable roles and team names.

Why use this skill?

Transform your OpenClaw agent into a professional dispatcher. Delegate complex, multi-part tasks to a specialized team of five sub-agents for parallel processing.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/be1human/multi-agent-en
Or

What This Skill Does

The Multi-Agent Dispatcher (English) skill transforms your primary OpenClaw agent into a high-level orchestration hub. Rather than attempting to handle complex, multi-faceted workflows itself, the Dispatcher acts as a project manager, distributing tasks among five distinct sub-agents (Alpha through Echo). Utilizing the sessions_spawn command, this system enables parallel processing of independent tasks, significantly increasing throughput and quality for multifaceted requests. The system employs a sophisticated round-robin scheduling mechanism, ensuring that if one agent is currently occupied, the workload is dynamically balanced across the available team members, preventing bottlenecks and allowing for concurrent research, development, and analytical operations.

Installation

To integrate this orchestration layer into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/be1human/multi-agent-en Once installed, you can modify the personality profiles of the sub-agents within the configuration files to suit your specific project requirements, whether you prefer a corporate structure, a creative studio, or a specialized technical research team.

Use Cases

  • Software Development Lifecycle: Delegate architecture analysis to one agent, bug fixing to another, and documentation to a third, all simultaneously.
  • Complex Market Research: Task the 'Scout' agent with data gathering while another agent synthesizes the findings into a report.
  • Content Production: Coordinate multiple drafting sessions for different chapters or sections of a project in parallel.

Example Prompts

  1. "I need to refactor the authentication module in our codebase. Please have someone analyze the architecture, someone write the unit tests, and someone draft the updated integration documentation."
  2. "Research the latest trends in AI agents for Q4, perform a competitive analysis on three main platforms, and summarize the findings into a concise internal briefing."
  3. "Prepare a strategic plan for our upcoming product launch. Divide the tasks: market entry strategy, technical requirements checklist, and social media outreach calendar."

Tips & Limitations

To get the most out of this skill, ensure your tasks are clearly defined. If a request has strict dependencies, instruct the Dispatcher to wait for the preceding output before spawning the next sub-agent. Remember that the Dispatcher does not perform execution itself; it is purely a routing agent. Over-partitioning simple, atomic tasks may lead to unnecessary overhead, so reserve this skill for complex, multi-stage, or high-volume projects.

Metadata

Author@be1human
Stars1776
Views1
Updated2026-03-02
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-be1human-multi-agent-en": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#multi-agent#orchestration#productivity#automation
Safety Score: 5/5

Related Skills

naruto-multi-agent-cn

Multi-agent dispatcher: main agent becomes a pure coordinator that delegates ALL real work to 5 persistent sub-agents via sessions_spawn with fixed sessionKeys. Round-robin scheduling, speak-before-spawn protocol, session reuse. Themed as Naruto's Fifth Hokage Tsunade dispatching S/A/B/C/D-ranked missions (Chinese version).

be1human 4473

respond-first

Multi-agent dispatcher skill. Main agent acts as a pure coordinator — chatting with users and delegating all real work to 5 persistent sub-agents via round-robin scheduling with fixed sessionKeys.

be1human 4473

multi-agent-cn

通用多Agent调度系统(中文版):将主Agent变为纯调度员,所有任务通过 sessions_spawn 委派给5个持久化子Agent。支持轮询调度、先回复再派遣协议、 sessionKey固定复用。用户可自定义调度员角色和子Agent名称/人设。

be1human 4473

clawphone-wechat-control

处理微信会话列表、进入聊天、发送消息、处理微信内弹窗与聊天页失败排查。适用于用户要求查看微信消息、回复联系人、转发、处理聊天输入框或发送失败时。执行时必须先确认当前在微信的哪个页面,再按聊天场景一步一验。

be1human 4473

clawphone-phone-control

使用手机控制 MCP 完成手机界面感知与操作。适用于读取当前手机状态、打开 App、处理弹窗、点击控件、输入文本、排查手机自动化失败等场景。执行时优先读取界面状态,涉及坐标点击时必须基于当前截图临时判定,禁止把历史坐标当成通用规则。

be1human 4473