Home Tutorials Categories Skills About
ZH EN JA KO
👥

Team Tasks

Multi-Agent Developer Tools

Install Command

npx clawhub@latest install team-tasks

Installation Guide

1
Check Environment

Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.

2
Run Installation

Run the install command above in your terminal. ClawHub will automatically download and install Team Tasks to the ~/.openclaw/skills/ directory.

3
Verify Installation

Run openclaw skills list to check your installed skills and confirm Team Tasks appears in the list.

4
Configure (Optional)

Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.

Manual Installation: Copy the Skill folder to ~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.
Multi-Agent Orchestration DAG Workflows Task Coordination

Detailed Description

The Team Tasks skill provides advanced multi-agent orchestration capabilities, enabling multiple AI agents to collaboratively complete complex tasks using different collaboration modes.

Core Features

  • Linear Mode: Agents execute tasks sequentially, with each agent's output serving as the next agent's input
  • DAG Mode: Define task dependencies as a directed acyclic graph, supporting parallel execution
  • Debate Mode: Multiple agents propose different solutions to the same problem, reaching consensus through discussion
  • Task Decomposition: Automatically break down complex tasks into assignable subtasks
  • Progress Tracking: Real-time display of each agent's execution progress and results

Configuration

{
  skills: {
    "team-tasks": {
      defaultMode: "dag",
      maxAgents: 5,
      timeout: 300         // Task timeout (seconds)
    }
  }
}

Use Cases

  • Multi-step research tasks: one agent searches, one analyzes, one summarizes
  • Code review: multiple agents review code from different angles (security, performance, readability)
  • Solution discussion: have agents debate a technical decision from multiple perspectives