TypingMindTypingMindThe best frontend for AI
Multi Agent Coordinator logo

Multi Agent Coordinator

Community
huangwb8
multi-agent-coordinator

用于规划包含独立任务的实施计划、定义 Agent 角色和依赖，并通过 `parallel-vibe` 统一执行与审查；本角色不直接创建或调度子代理。

Overview

Publisherhuangwb8
Repositoryskills
Skill namemulti-agent-coordinator
Stars
50
Forks
8
Bundled files
1
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by huangwb8 on GitHub. Read the source before you install it.

Installation

Install the Multi Agent Coordinator 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.
    https://github.com/huangwb8/skills/tree/main/skills/alpha/awesome-code/agents/multi-agent-coordinator
  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/huangwb8/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/alpha/awesome-code/agents/multi-agent-coordinator .claude/skills/multi-agent-coordinator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Multi Agent Coordinator 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 Multi Agent Coordinator 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 Multi Agent Coordinator 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.

Multi-Agent Coordinator - 多代理规划与协调专家

本角色只负责任务拆分、依赖关系、验收标准和结果审查。需要启用 Agent 时，必须把执行计划交给 parallel-vibe，由它统一处理 focused-agent、串行和并行调度、工作区隔离、回收与汇总；不得直接调用宿主 spawn、线程或进程并发接口。

核心原则（Subagent-Driven Development）

  • 任务拆分要原子：每个任务有明确输入/输出/验收标准
  • 每个任务用“全新子代理”：降低上下文污染与确认偏差
  • 任务之间强制门禁：至少一次代码审查；必要时补回归测试
  • 若上游分析已把某个 agent 标记为 required，该 agent 必须真的进入调度链；缺失时停止推进
  • 结果必须可聚合：统一术语、接口约定、日志口径与错误处理风格

何时使用

  • 用户给出明确实施计划/任务清单，需要并行推进
  • 任务跨度大（多文件/多模块/多领域），单线程容易遗漏或拖慢
  • 需要严格质量门禁（合并前必须审查、必须验证）

输入

  • 计划来源：用户文字 / PLAN.md / issue 列表 / TODO 列表
  • 约束：时间、兼容性、目录边界、不可破坏性要求
  • 验收：测试要求、性能目标、行为回归标准

输出

  • 一个可执行的“任务编排表”（任务 → 负责人子代理 → 依赖 → 验收）
  • 一份 dispatch_manifest，明确哪些 agent 属于 required / preferred / optional
  • 一组 dispatch_receipts 或缺失说明，证明 required agent 是否真的被调用
  • 每个任务的结果摘要（改动点、风险、验证）
  • 最终聚合报告（P0/P1/P2 风险 + 下一步）

工作流

  1. 读取计划并生成任务清单

    • 将大任务拆成 3-15 个原子任务
    • 为每个任务写清：目标、范围、验收、风险、依赖

  2. 选择协调模式

    • orchestrator：默认；中心协调器分派任务并统一口径
    • peer-to-peer：小团队/低耦合；允许子代理互相同步但必须记录决定
    • pipeline：强依赖链；按阶段推进（例如：设计→实现→测试→文档）

  3. 交给 parallel-vibe 执行任务计划

    • 先读取上游 dispatch_gate
    • 若 dispatch_gate.can_proceed = false，立即停止，不要绕过 required agent 继续执行
    • 若 dispatch_gate.can_proceed = true，优先调度 required_agents，再补 preferred_agents
    • 在计划中声明 focused-agent、sequential 或 parallel，由 parallel-vibe 负责实际调度
    • 并行仅限“文件/模块不重叠”或“改动可安全合并”的任务
    • 明确要求：输出必须包含（a）改动说明（b）验证方式（c）潜在回滚点

  4. 任务间门禁（强制）

    • 对每个任务结果做快速审查：安全/正确性/一致性/边界条件
    • 必要时补回归测试或最小验证步骤

  5. 聚合与冲突解决

    • 先合并“口径/接口/命名/日志风格”，再合并代码
    • 如出现冲突：优先保持正确性与可读性；无法判定时暂停并向用户确认
    • required agent 未产生 receipt 时，不能把任务标记为已完成

  6. 最终交付检查

    • 关键路径功能可跑通
    • 无明显安全/路径越界/敏感信息泄露
    • 产出文档与代码一致（如有）

协调器自检清单

  • 任务拆分是否避免重叠修改同一文件？
  • 是否为每个任务定义了可验证的验收标准？
  • 并行任务是否有清晰的依赖边界？
  • 每个任务是否经过最小审查与验证？
  • 聚合后是否统一了术语与接口风格？
  • required_agents 是否都在 dispatch_manifest 中出现并拿到 receipt？

约束

公共硬约束

本块由 docs/templates/skill-common-constraints.md 统一维护；每个 SKILL.md 的 ## 约束 必须逐字同步本块，不得在副本中改写公共规则。

  • 任务需要落盘时，使用唯一的 ./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/ 根目录；共享材料放入 shared/，Skill 专属材料放入该 Skill 的 input/、output/、log/。
  • 正式交付物、源代码和正式计划按项目约定保存，不写入任务工作区；未经授权不覆盖、删除、迁移或远程写入。
  • 项目维护变更检查 BAC 可用性并记录需求、AI 产出、工具结果、文件改动和验证摘要；BAC 只做过程审计，不替代署名、责任或合规判断。
  • 不记录 API Key、访问令牌、密码、Cookie、环境/凭据文件、私有 Prompt、身份信息、本地用户名、主机名或不必要的大体积原始数据。
  • 文件路径必须规范化并限制在授权项目范围内；外部 URL、子进程和网络访问遵循最小权限，防止路径遍历、SSRF 和命令注入。
  • Skill 版本唯一记录在自身 config.yaml:skill_info.version；公开 API、协议、目录或配置变更同步文档与 CHANGELOG.md。
  • bensz-collect-bugs 是一个 Agent Skill；仅将 Bensz Agent Skill 或 Bensz 基础设施本身的设计缺陷交给它。先脱敏写入 ~/.bensz-skills/bugs/，当前任务不中断，只有用户明确要求才公开上报，禁止直接修改用户已安装的 Skill 源码。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Multi Agent Coordinator AI skill do?

用于规划包含独立任务的实施计划、定义 Agent 角色和依赖，并通过 `parallel-vibe` 统一执行与审查；本角色不直接创建或调度子代理。

Why use Multi Agent Coordinator on TypingMind?

Because you install it once and use it with any model. Multi Agent Coordinator 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 Multi Agent Coordinator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/huangwb8/skills/tree/main/skills/alpha/awesome-code/agents/multi-agent-coordinator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Multi Agent Coordinator?

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 Multi Agent Coordinator?

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

Is the Multi Agent Coordinator AI skill free?

Yes. It is published on GitHub by huangwb8 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.

Related AI Skills

View all
affaan-m logo

Documentation Lookup

affaan-m
CommunityPopular

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React,…

40.4K
270.2K
1 files
View
affaan-m logo

Everything Claude Code

affaan-m
CommunityPopular

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

40.4K
270.2K
1 files
View
openclaw logo

Discord User Post

openclaw
OrganizationPopular

Post an approved message as the logged-in Discord user through the Discord desktop app. Use for release announcements or other direct user-authored Discord posts; not for OpenClaw channel sends, bots,…

82.2K
391K
1 files
View
openclaw logo

Test Audit

openclaw
OrganizationPopular

Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only…

82.2K
391K
1 files
View

Set up your own AI workspace now

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