Dispatching Parallel Agents logo

Dispatching Parallel Agents

CommunityPopular
jnMetaCode
dispatching-parallel-agents

当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用

Overview

PublisherjnMetaCode
Repositorysuperpowers-zh
Skill namedispatching-parallel-agents
Stars
8.1K
Forks
758
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jnMetaCode on GitHub. Read the source before you install it.

Installation

Install the Dispatching Parallel Agents AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git /tmp/superpowers-zh
mkdir -p .claude/skills
cp -r /tmp/superpowers-zh/skills/dispatching-parallel-agents .claude/skills/dispatching-parallel-agents
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dispatching Parallel Agents in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dispatching Parallel Agents on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dispatching Parallel Agents is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

并行分派智能体

概述

你将任务委派给具有隔离上下文的专用智能体。通过精心设计它们的指令和上下文,确保它们专注并成功完成任务。它们不应继承你的会话上下文或历史记录——你要精确构造它们所需的一切。这样也能为你自己保留用于协调工作的上下文。

当你遇到多个不相关的失败(不同的测试文件、不同的子系统、不同的 bug),逐一排查会浪费时间。每个排查都是独立的,可以并行进行。

核心原则: 每个独立问题域分派一个智能体,让它们并发工作。

何时使用

dot
digraph when_to_use {
    "存在多个失败?" [shape=diamond];
    "它们是否独立?" [shape=diamond];
    "单个智能体排查所有问题" [shape=box];
    "每个问题域一个智能体" [shape=box];
    "能否并行工作?" [shape=diamond];
    "顺序执行智能体" [shape=box];
    "并行分派" [shape=box];

    "存在多个失败?" -> "它们是否独立?" [label="是"];
    "它们是否独立?" -> "单个智能体排查所有问题" [label="否 - 有关联"];
    "它们是否独立?" -> "能否并行工作?" [label="是"];
    "能否并行工作?" -> "并行分派" [label="是"];
    "能否并行工作?" -> "顺序执行智能体" [label="否 - 有共享状态"];
}

适用场景:

  • 3 个以上测试文件因不同根因失败
  • 多个子系统独立出现故障
  • 每个问题无需其他问题的上下文即可理解
  • 排查之间无共享状态

不适用场景:

  • 失败是相关的(修复一个可能修复其他的)
  • 需要理解完整的系统状态
  • 智能体之间会互相干扰

模式

1. 识别独立的问题域

按故障分组:

  • 文件 A 测试:工具审批流程
  • 文件 B 测试:批量完成行为
  • 文件 C 测试:中止功能

每个问题域是独立的——修复工具审批不会影响中止测试。

2. 创建聚焦的智能体任务

每个智能体获得:

  • 明确范围: 一个测试文件或子系统
  • 清晰目标: 让这些测试通过
  • 约束条件: 不修改其他代码
  • 预期输出: 你发现和修复内容的总结

3. 并行分派

typescript
// 在 Claude Code / AI 环境中
Task("修复 agent-tool-abort.test.ts 的失败")
Task("修复 batch-completion-behavior.test.ts 的失败")
Task("修复 tool-approval-race-conditions.test.ts 的失败")
// 三个任务并发运行

4. 审查与集成

当智能体返回时:

  • 阅读每个总结
  • 验证修复之间没有冲突
  • 运行完整测试套件
  • 集成所有更改

智能体提示词结构

好的智能体提示词应该是:

  1. 聚焦的 - 一个清晰的问题域
  2. 自包含的 - 包含理解问题所需的所有上下文
  3. 明确输出要求 - 智能体应该返回什么?
markdown
修复 src/agents/agent-tool-abort.test.ts 中 3 个失败的测试:

1. "should abort tool with partial output capture" - 期望消息中包含 'interrupted at'
2. "should handle mixed completed and aborted tools" - 快速工具被中止而非完成
3. "should properly track pendingToolCount" - 期望 3 个结果但得到 0 个

这些是时序/竞态条件问题。你的任务:

1. 阅读测试文件,理解每个测试验证的内容
2. 找到根因——是时序问题还是实际 bug?
3. 修复方式:
   - 用基于事件的等待替换任意超时
   - 如果发现中止实现中的 bug 则修复
   - 如果测试的是已变更的行为则调整测试期望

不要只是增加超时时间——找到真正的问题。

返回:你发现了什么以及修复了什么的总结。

常见错误

错误做法:太宽泛: "修复所有测试" - 智能体会迷失方向 正确做法:具体明确: "修复 agent-tool-abort.test.ts" - 聚焦的范围

错误做法:无上下文: "修复竞态条件" - 智能体不知道在哪里 正确做法:提供上下文: 粘贴错误信息和测试名称

错误做法:无约束: 智能体可能会重构所有代码 正确做法:设置约束: "不要修改生产代码" 或 "只修复测试"

错误做法:模糊的输出要求: "修好它" - 你不知道改了什么 正确做法:明确要求: "返回根因和修改内容的总结"

不适用的场景

关联性失败: 修复一个可能修复其他的——先一起排查 需要完整上下文: 理解问题需要看到整个系统 探索性调试: 你还不知道什么坏了 共享状态: 智能体会互相干扰(编辑同一文件、使用同一资源)

实际案例

场景: 大规模重构后,3 个文件中出现 6 个测试失败

失败情况:

  • agent-tool-abort.test.ts:3 个失败(时序问题)
  • batch-completion-behavior.test.ts:2 个失败(工具未执行)
  • tool-approval-race-conditions.test.ts:1 个失败(执行计数 = 0)

决策: 独立的问题域——中止逻辑、批量完成、竞态条件各自独立

分派:

智能体 1 → 修复 agent-tool-abort.test.ts
智能体 2 → 修复 batch-completion-behavior.test.ts
智能体 3 → 修复 tool-approval-race-conditions.test.ts

结果:

  • 智能体 1:用基于事件的等待替换了超时
  • 智能体 2:修复了事件结构 bug(threadId 位置不对)
  • 智能体 3:添加了等待异步工具执行完成的逻辑

集成: 所有修复互相独立,无冲突,完整测试套件全部通过

验证

智能体返回后:

  1. 审查每个总结 - 理解改了什么
  2. 检查冲突 - 智能体是否编辑了同一段代码?
  3. 运行完整套件 - 验证所有修复协同工作
  4. 抽查 - 智能体可能犯系统性错误

Frequently asked questions

What does the Dispatching Parallel Agents AI skill do?

当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用

Why use Dispatching Parallel Agents on TypingMind?

Because you install it once and use it with any model. Dispatching Parallel Agents is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dispatching Parallel Agents in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/dispatching-parallel-agents. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dispatching Parallel Agents?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dispatching Parallel Agents?

As many as you like. As long as a model supports skills, you can use Dispatching Parallel Agents with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dispatching Parallel Agents AI skill free?

Yes. It is published on GitHub by jnMetaCode under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇