Communitygithub.com

团队智能体编排

使用工作项、所有权、智能体看板、合并门禁和控制面板交接,对智能体团队进行基于团队的编排。当需要协调一个智能体团队并涉及工作项、所有权、看板和合并门禁时使用。

团队智能体编排 是什么?

这个专业技能旨在解决多智能体协作场景下的编排问题,其核心是将智能体视为拥有明确契约的团队成员,而非单一的助手。它通过引入工作项(Work Item)、所有权(Ownership)、智能体看板(Agent Kanban)、分支隔离(Branch Isolation)、控制面板(Control Pane)和合并门禁(Merge Gate)等概念,构建了一个可靠、可见的团队协作框架。该技能支持多种执行模式,包括单智能体、动态工作流、tmux/Zellij 多窗口、工作树(worktree)并行执行以及外部桌面编排器。其价值在于解决常见的失败模式,如“智能体汤”(无主、无门禁的混乱并发)、“不可见的工作”(仅存在于聊天记录的输出)和“重叠写入”(并行智能体无隔离地修改同一文件)。最终,每次编排都应以板/卡更新、合并或待合并分支、测试与评估证据、阻塞项以及可复用的专业技能候选为产出,从而确保团队化智能体工作的可管理性与可交付性。

兼容平台✓Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/team-agent-orchestration

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

团队智能体编排 是做什么的?

当智能体是像团队一样管理而非单一助手时,使用本技能。其目的是使基于团队的编排变得可靠:清晰的工作项、明确的所有权、智能体看板状态、分支隔离、控制面板可见性和合并门禁。

何时激活

  • 任务跨越多个智能体、工具、工具集、分支或工作树。
  • 用户提及团队编排、智能体看板、小队(squad)、指挥者(conductor)、控制面板、管理者(manager)、桌面应用、Zellij、tmux、Hermes、Devin、Codex、Claude Code 或多智能体工作。
  • 项目需要在人员和智能体之间共享工作流状态。
  • 现有的智能体扇出模式虽然产生输出,但生成的产物无法合并。

运行模型

将每个智能体视为一个拥有狭窄契约的队友:

  • 所有者:对工作项负责的人或智能体。
  • 范围:文件、分支、工具表面和禁止区域。
  • 状态:待办(backlog)、就绪(ready)、运行中(running)、审查(review)、阻塞(blocked)、已合并(merged)或已归档(archived)。
  • 证据:测试、截图、日志、审查记录或评估报告。
  • 合并门禁:允许集成的确切条件。

智能体看板

当工作需要跨会话可见时,使用智能体看板。

列含义退出标准
待办(Backlog)候选工作项,尚未明确成形编写验收标准
就绪(Ready)已成形并可分配已分配所有者和分支/工作树
运行中(Running)智能体正在积极工作交接产物和已更改的文件存在
审查(Review)工作完成但未合并测试、差异审查和风险评估通过
阻塞(Blocked)需要外部输入或门禁失败阻塞项具有所有者和下一步操作
已合并(Merged)已集成到主分支PR 已合并或本地主分支已更新
已归档(Archived)不再相关记录原因

每个卡片应遵循此结构:

{
  "id": "agent-card-001",
  "title": "构建动态工作流专业技能",
  "owner": "codex",
  "state": "running",
  "branch": "product/dynamic-workflow-team-orchestration",
  "worktree": ".",
  "acceptance": [
    "专业技能存在",
    "测试涵盖所需概念",
    "内容产物包含视频和文章角度"
  ],
  "merge_gate": "lint、聚焦测试和目录检查均通过",
  "handoff": "path/to/handoff.md"
}

基于团队的编排流程

  1. 塑造看板:将模糊的雄心转化为带有所有者和合并门禁的工作项。
  2. 选择执行模式:单智能体、动态工作流模式、dmux/tmux、工作树扇出模式或外部桌面编排器。
  3. 分配边界:每个卡片一个所有者,清晰的文件范围,没有集成者的情况下不允许重叠写入。
  4. 运行智能体:每个智能体同时编写证据和交接说明,而不仅仅是代码。
  5. 按序审查:先测试,再差异审查,然后安全/风险评估,最后内容/产品打磨。
  6. 有意图地合并:一个集成者解决冲突并更新控制面板或状态产物。
  7. 提取可复用专业技能:如果卡片模式重复出现,将其提升到 skills/ 目录。

控制面板要求

一个用于团队编排的有用的控制面板应显示:

  • 活跃的工作项及其智能体看板状态。
  • 所有者、工具集、分支、工作树和最后心跳。
  • 指向交接产物、测试、截图和 PR 的链接。
  • 按所有者分组的阻塞项及其解除阻塞动作。
  • 按门禁(而非直觉)指示的合并就绪状态。
  • 应成为共享专业技能的可复用工作流候选。

在操作者能够回答以下问题之前,不要添加更多自动化:谁拥有这个?什么发生了变化?哪个门禁失败了?哪些内容可以安全合并?

动态工作流兼容性

当卡片需要动态工作流模式时:

  • 将任务本地的工具集放在卡片所有者的管辖下。
  • 将输入和输出存储在卡片上。
  • 在从“运行中”转移到“审查”之前,需要进行一次评估。
  • 仅在该工具集重复使用后,才将其提升为共享专业技能。

需关注的失败模式

  • 智能体汤:许多智能体同时运行,但没有所有者或合并门禁。
  • 不可见的工作:有用的输出仅存在于聊天记录中。
  • 看板表演:看板存在,但卡片没有验收标准。
  • 重叠写入:没有工作树隔离时,并行智能体编辑相同文件。
  • 无产物产物:流程产生了文档,但没有可运行或可发布的成果。

输出标准

每次编排过程结束时,应产出:

  • 看板/卡片的变更。
  • 已合并或待合并的分支。
  • 测试和评估证据。
  • 带有所有者和下一步操作的阻塞项。
  • 新的共享专业技能候选。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

相关技能