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.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/be1human/respond-firstWhat This Skill Does
The respond-first skill transforms your OpenClaw agent into a specialized orchestrator. Unlike standard agents that attempt to juggle all tasks internally, this skill enforces a strict separation of concerns. It acts as a dedicated dispatcher, managing a pool of 5 persistent sub-agents labeled alpha through echo. By delegating execution to these specific session-keyed agents, the system maintains context isolation, prevents task contamination, and ensures that heavy-duty processing doesn't bottleneck the user interface.
Installation
To integrate this skill into your environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/be1human/respond-first
Ensure your local environment is configured to support persistent session keys, as this skill relies on the session persistence layer of the OpenClaw framework.
Use Cases
This skill is ideal for multi-tenant or complex project environments where you need consistent, specialized performance. It is particularly effective for teams requiring a 'single point of contact' interface while offloading work to a background swarm. For instance, developers can use it to maintain a clean chat history while delegating architecture reviews to bravo and bug fixes to delta simultaneously, keeping the primary communication channel uncluttered.
Example Prompts
- "I need a deep analysis of the project's memory leaks. Please investigate using the available sub-agents."
- "Search for the latest documentation on the new API endpoints and create a summary for me."
- "The current CSS in the dashboard is broken; assign someone to fix this immediately."
Tips & Limitations
- Strict Protocol: Always remember the 'Speak First, Then Spawn' rule. If you do not provide a conversational response before triggering a tool call, the user interface may appear unresponsive.
- Session Management: The 5-agent limit is hardcoded. Use the round-robin scheduler effectively—if a task is critical, consider if the assigned agent is already overloaded.
- No Local Execution: As a pure coordinator, this skill lacks file-write or execution permissions. It acts as an abstraction layer; you must ensure your sub-agents have the necessary permissions granted in their respective configurations to actually complete the work being dispatched to them.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-be1human-respond-first": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
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).
naruto-multi-agent
Naruto-themed multi-agent dispatcher. You are Tsunade, the 5th Hokage, assigning missions to 5 elite shinobi (sub-agents). Automatic mission rank assessment (S/A/B/C/D), immersive roleplay, and round-robin dispatch.
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。
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。
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。