跳到正文
TakoAPI
返回技能列表

multi-agent-collab

由 vdc-k 提供

AI & LLMs
—暂无评分
你的评分

简介

Universal multi-agent collaboration methodology for Claude Code.

描述

该技能的功能

A coordination protocol for teams of AI agents working on shared projects. Assigns roles by model capability: a lead model handles architecture and decisions, an engineer model handles execution, and a maintainer model handles archiving. Three shared documents (TASK.md, CHANGELOG.md, CONTEXT.md) act as the sync layer, with QMD indexing enabling on-demand context retrieval instead of full history injection.

Tiered model roles cut token costs by reserving expensive models for high-level decisions while cheaper models handle routine execution and archiving.

何时使用

  • Running an expensive model for architecture decisions while cheaper models write code
  • Tracking task status across multiple agent sessions with a shared TASK.md
  • Generating weekly progress reports by aggregating tagged CHANGELOG entries
  • Flagging repeated agent workflows as candidate reusable skills
  • Coordinating parallel agents on a shared codebase without context conflicts

示例工作流

输入

User asks: implement a new API endpoint using multiple agents

智能体
  1. 1

    Lead model queries QMD index to retrieve relevant TASK.md fragments

  2. 2

    Lead model breaks the feature into subtasks and updates TASK.md

  3. 3

    Engineer model implements the endpoint and writes tests

  4. 4

    Engineer model appends a tagged CHANGELOG entry and marks tasks complete

  5. 5

    Maintainer model archives completed entries and flags any pattern occurring 3 or more times as a candidate skill

输出

Endpoint implemented with synchronized TASK.md, a new CHANGELOG entry, and a candidate skill flagged if the workflow pattern recurred

前置要求

  • qmd indexing tool

安装

clawhub install vdc-k/multi-agent-collab

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接