Agent skill

A2a Task Decompose

by Leochens in Leochens/feishu-bot-chat-plugin

A2A 任务分解与分配指南。仅在飞书群聊中使用,私聊时不适用. An agent skill from Leochens/feishu-bot-chat-plugin.

MITAuto-check passed

Install A2a Task Decompose

skills CLI
$ npx skills add Leochens/feishu-bot-chat-plugin --skill a2a-task-decompose -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Leochens/feishu-bot-chat-plugin a2a-task-decompose --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Leochens/feishu-bot-chat-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/a2a-task-decompose .claude/skills/a2a-task-decompose && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
a2a-task-decompose
GitHub stars
156
Token cost
~459 tokens
SKILL.md length
94 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

A2A 任务分解与分配指南。仅在飞书群聊中使用,私聊时不适用. An agent skill from Leochens/feishu-bot-chat-plugin.

  • Works in 6 steps: 理解需求 — 明确用户的最终目标和交付物 → 识别子任务 — 按职能拆分,每个子任务对应一个 bot 的能力 → 确定依赖 — 哪些可以并行,哪些必须串行 → …
  • SKILL.md covers 核心原则:任务闭环, 分解流程, 依赖关系模式 and 任务分配消息模板, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

A2a Task Decompose is an agent skill from Leochens/feishu-bot-chat-plugin. A2A 任务分解与分配指南。仅在飞书群聊中使用,私聊时不适用。 当以下情况时使用此 Skill: (1) 用户提出复杂需求,需要多个 bot 协作完成 (2) 需要将大任务拆解成子任务并分配给不同 bot (3) 用户说"群内协作"、"分配任务"等关键字 (4) 需要规划多 bot 协作的执行顺序

Its SKILL.md is about 460 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: OpenClaw plugin for bot-to-bot @ communication in Feishu group chats. The licence is MIT.

Example prompts

  • “/a2a-task-decompose”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 理解需求 — 明确用户的最终目标和交付物
  2. 识别子任务 — 按职能拆分,每个子任务对应一个 bot 的能力
  3. 确定依赖 — 哪些可以并行,哪些必须串行
  4. 逐个分配 — 每次回复只 @ 1 个 bot,串行发起
  5. 等待回传 — 每个子 Agent 完成后会 @ 回你,收到后再进行下一步
  6. 汇总交付 — 所有子任务完成后,整理结果回复用户

What it can do on your machine

Read from SKILL.md and the folder at commit 69b0fdc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

A2a Task Decompose loads about 459 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 94 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~459

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Leochens/feishu-bot-chat-plugin at commit 69b0fdc, republished under its MIT licence (© Leochens). 94 words, ~459 tokens.

Download SKILL.mdSave it as .claude/skills/a2a-task-decompose/SKILL.md (or your agent's skills folder).
name
a2a-task-decompose
description
A2A 任务分解与分配指南。**仅在飞书群聊中使用,私聊时不适用。** **当以下情况时使用此 Skill**: (1) 用户提出复杂需求,需要多个 bot 协作完成 (2) 需要将大任务拆解成子任务并分配给不同 bot (3) 用户说"群内协作"、"分配任务"等关键字 (4) 需要规划多 bot 协作的执行顺序
alwaysActive
true

A2A 任务分解与分配

核心原则:任务闭环

所有通过 @ 分配出去的任务,子 Agent 完成后必须 @ 回你汇报结果。 这是协作能运转的基础——你需要知道每个子任务的进展和结果,才能汇总回复用户。

分解流程

  1. 理解需求 — 明确用户的最终目标和交付物
  2. 识别子任务 — 按职能拆分,每个子任务对应一个 bot 的能力
  3. 确定依赖 — 哪些可以并行,哪些必须串行
  4. 逐个分配 — 每次回复只 @ 1 个 bot,串行发起
  5. 等待回传 — 每个子 Agent 完成后会 @ 回你,收到后再进行下一步
  6. 汇总交付 — 所有子任务完成后,整理结果回复用户

依赖关系模式

串行链(A → B → C)

适用于:后一步依赖前一步的输出

第 1 轮:@ 产品 → "请整理需求文档"
         等待产品 @ 回你,带上需求文档
第 2 轮:@ 后端 → "根据以下需求设计接口:{产品的输出}"
         等待后端 @ 回你,带上接口设计
第 3 轮:@ 前端 → "根据以下接口对接前端:{后端的输出}"
         等待前端 @ 回你,带上实现结果
第 4 轮:汇总所有结果,回复用户
并行扇出(A → B, A → C)

适用于:多个子任务互不依赖

第 1 轮:@ 后端 → "请设计用户模块的数据库方案"
         等待后端 @ 回你
第 2 轮:@ 前端 → "请设计用户模块的页面原型"
         等待前端 @ 回你
第 3 轮:汇总两方结果,回复用户

注意:因为每次只能 @ 1 个 bot,"并行"实际上是依次发起,但各子任务之间不互相依赖。

任务分配消息模板

<at user_id="ou_xxxx">bot名字</at>

**任务**:{一句话描述任务}

**背景**:{必要的上下文信息}

**预期输出**:{明确的交付物格式}

**注意事项**:{约束条件或特殊要求}

完成后请 @ 回我汇报结果。
示例
<at user_id="ou_xxxx">mac-后端</at>

**任务**:设计用户注册接口

**背景**:我们在做一个新的用户系统,需要支持手机号和邮箱两种注册方式

**预期输出**:接口文档,包含 URL、请求参数、响应格式、错误码

**注意事项**:需要考虑防刷和频率限制

完成后请 @ 回我汇报结果。

选择合适的 bot

根据可用机器人列表中的描述匹配:

任务类型适合分配给
需求分析、PRD 编写产品类 bot
接口设计、数据库方案后端类 bot
页面实现、交互设计前端类 bot
测试用例、质量检查测试类 bot
部署、CI/CD、监控运维类 bot

注意事项

  • 分配任务前先确认该 bot 在可用列表中
  • 任务描述要具体,避免模糊指令如"帮我看看"
  • 如果子任务的输出是下一个 bot 的输入,在分配时附上前一步的结果
  • 预估每个子任务的复杂度,复杂任务给充分的上下文
  • 分配消息末尾加上"完成后请 @ 回我汇报结果",确保子 Agent 知道要回传
  • 持续运行的服务:如果子任务产出是需要持续运行的服务(API server、dev server 等),必须在分配时明确要求对方用 pm2 或 nohup 启动,确保服务在回复后仍然存活。回传结果时应附上服务地址和停止命令

© Leochens, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/a2a-task-decompose of Leochens/feishu-bot-chat-plugin.

Open the folder on GitHubat commit 69b0fdc

Compare with similar skills

A2a Task Decompose next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

A2a Task Decompose compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
A2a Task Decompose this skillLeochens/feishu-bot-chat-plugin156—~459Automated safety check: PassMIT
OmniRoute A2A CLIdiegosouzapw/OmniRoute74k—~423Automated safety check: PassMIT
A2a ProtocolBuilderIO/agent-native7.1k—~5.7kAutomated safety check: PassNone
A2a Protocolinternet-court/internet-court-skill6.4k1 repos~2.5kAutomated safety check: PassApache-2.0
OmniRoute A2A Agentsdiegosouzapw/OmniRoute74k—~794Automated safety check: PassMIT
Decompose Gateshappier-dev/happier1.9k—~1.5kAutomated safety check: PassMIT

Similar skills

  • OmniRoute A2A CLI

    diegosouzapw/OmniRoute

    Sends tasks, inspects skill execution history, and tests OmniRoute's JSON-RPC 2.0 agent-to-agent server from the command line.

    74k GitHub stars~423 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • A2a Protocol

    BuilderIO/agent-native

    How agent-native apps discover, authenticate with, and call each other over A2A.

    7.1k GitHub stars~5.7k tokensUpdated today
    DevelopmentAuto-check passed
  • A2a Protocol

    internet-court/internet-court-skill

    Builds Agent-to-Agent (A2A) servers and clients following Google's open protocol for agent interoperability.

    6.4k GitHub starsUsed in 1 repo~2.5k tokens
    Productivity & AutomationAuto-check passed
  • OmniRoute A2A Agents

    diegosouzapw/OmniRoute

    Explains how to call OmniRoute over JSON-RPC 2.0 using the agent-to-agent protocol, including its Agent Card, built-in skills, call shape and error codes.

    74k GitHub stars~794 tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Decompose Gates

    happier-dev/happier

    Decompose a hard or multi-part task into independently checkable pieces with explicit verification gates and risk-weighted ordering.

    1.9k GitHub stars~1.5k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Time Series Decomposer

    jeremylongshore/tons-of-skills-marketplace

    Manage time series decomposer operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~570 tokensUpdated today
    Data & AnalyticsAuto-check passed

More from Leochens/feishu-bot-chat-plugin

  • A2a Collaboration Guide

    Leochens/feishu-bot-chat-plugin

    A2A 群内协作规则速查手册。仅在飞书群聊中使用,私聊时不适用. An agent skill from Leochens/feishu-bot-chat-plugin.

    156 GitHub stars~522 tokensUpdated 3 mo ago
    Auto-check passed
  • A2a Interrupt

    Leochens/feishu-bot-chat-plugin

    A2A 协作中断与取消处理指南。仅在飞书群聊中使用,私聊时不适用. An agent skill from Leochens/feishu-bot-chat-plugin.

    156 GitHub stars~289 tokensUpdated 3 mo ago
    Auto-check passed
  • A2a Mode Switch

    Leochens/feishu-bot-chat-plugin

    A2A 协作模式切换指南。仅在飞书群聊中使用,私聊时不适用. An agent skill from Leochens/feishu-bot-chat-plugin.

    156 GitHub stars~293 tokensUpdated 3 mo ago
    Auto-check passed
  • A2a Result Merge

    Leochens/feishu-bot-chat-plugin

    A2A 多 bot 协作结果汇总指南。仅在飞书群聊中使用,私聊时不适用. An agent skill from Leochens/feishu-bot-chat-plugin.

    156 GitHub stars~303 tokensUpdated 3 mo ago
    Auto-check passed
  • A2a Status Check

    Leochens/feishu-bot-chat-plugin

    A2A 协作状态查询与进度汇报指南。仅在飞书群聊中使用,私聊时不适用. An agent skill from Leochens/feishu-bot-chat-plugin.

    156 GitHub stars~271 tokensUpdated 3 mo ago
    Auto-check passed

Questions about A2a Task Decompose

What does A2a Task Decompose do?

A2A 任务分解与分配指南。仅在飞书群聊中使用,私聊时不适用. An agent skill from Leochens/feishu-bot-chat-plugin. A2a Task Decompose is an agent skill from Leochens/feishu-bot-chat-plugin.

How do I install A2a Task Decompose in Claude Code?

Run `npx skills add Leochens/feishu-bot-chat-plugin --skill a2a-task-decompose -a claude-code`. Or copy the skill folder (skills/a2a-task-decompose in Leochens/feishu-bot-chat-plugin) into .claude/skills/a2a-task-decompose in your project. Claude Code loads it when a task matches its description.

How do I install A2a Task Decompose in Codex?

Run `npx skills add Leochens/feishu-bot-chat-plugin --skill a2a-task-decompose -a codex`. Or copy the skill folder (skills/a2a-task-decompose in Leochens/feishu-bot-chat-plugin) into .agents/skills/a2a-task-decompose in your project. Codex loads it when a task matches its description.

Can I use A2a Task Decompose in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Leochens/feishu-bot-chat-plugin --skill a2a-task-decompose -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/a2a-task-decompose, .gemini/skills/a2a-task-decompose, .github/skills/a2a-task-decompose and .opencode/skills/a2a-task-decompose in your project.

What does A2a Task Decompose need to run?

SKILL.md names no scripts, command-line tools or credentials: A2a Task Decompose is instructions for the agent only.

Does A2a Task Decompose access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is A2a Task Decompose safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does A2a Task Decompose use?

A2a Task Decompose is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does A2a Task Decompose use?

About 459 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to A2a Task Decompose?

Skills that share tags, products or a category with A2a Task Decompose: OmniRoute A2A CLI (diegosouzapw/OmniRoute, 74k stars), A2a Protocol (BuilderIO/agent-native, 7.1k stars), A2a Protocol (internet-court/internet-court-skill, 6.4k stars) and OmniRoute A2A Agents (diegosouzapw/OmniRoute, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains A2a Task Decompose?

Leochens (a GitHub user) maintains it in Leochens/feishu-bot-chat-plugin, which has 156 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on June 18, 2026.

Source: Leochens/feishu-bot-chat-plugin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.