Communitygithub.com

团队智能体编排

运行基于团队的编排,用于智能体小队,利用工作项、所有权、智能体看板、合并门控和控制面板交接。当需要协调一个由工作项、所有权、看板和合并门控组成的智能体小队时使用。

团队智能体编排 是什么?

此技能旨在管理多个 AI 智能体协同时,实现可靠、可重复的团队式编排。它将每个智能体视为一个有明确职责范围的团队成员,通过结构化的“智能体看板”跟踪从积压到存档的每个工作项的状态。每个工作项都包含明确的负责人、文件范围、验收标准和“合并门控”(代码融合前必须通过的特定条件),从而防止冲突并确保交付质量。该技能支持多种执行模式,包括单智能体、动态工作流和并行工作树,并建议使用一个中央“控制面板”来显示所有活动的实时状态、阻碍因素和合并准备情况。它通过提供从任务定义到代码审查再到刻意合并的标准化流程,解决了“智能体混乱”(角色和门控不明确)和“重叠写入”等常见问题。它兼容 Cursor、Codex 和 Claude Code 等平台,并指导用户将持续出现的工作模式提取为可复用的技能,使其成为从事复杂多智能体项目的开发团队的理想选择。

兼容平台✓Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/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?

当智能体像团队而非单个助手一样被管理时,使用此技能。其目的是使基于团队的编排可靠:明确的工作项、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控。

何时激活

  • 任务涉及多个智能体、工具、操控程序、分支或工作树。
  • 用户提及团队编排、智能体看板、小队、指挥、控制面板、经理、桌面应用、Zellij、tmux、Hermes、Devin、Codex、Claude Code 或多智能体工作。
  • 项目需要跨人员和智能体共享工作流状态。
  • 现有的智能体扇出正在产生输出,但产物不可合并。

运作模式

将每个智能体视为具有狭窄契约的队友:

  • 负责人:对工作项负责的个人或智能体。
  • 范围:文件、分支、工具界面和禁止区域。
  • 状态:积压、就绪、运行中、审查中、已阻塞、已合并或已归档。
  • 证据:测试、屏幕截图、日志、审查笔记或评估报告。
  • 合并门控:允许集成的确切条件。

智能体看板

当工作必须在会话之间保持可见时,使用智能体看板。

列含义退出标准
积压候选工作项,尚未成形验收标准已编写
就绪已成形并可分配负责人和分支/工作树已分配
运行中智能体正在积极工作交接产物和已更改的文件存在
审查中工作已完成但尚未合并测试、差异审查和风险检查通过
已阻塞需要外部输入或门控失败阻塞项有负责人和下一步行动
已合并已集成到主线PR 已合并或本地主线已更新
已归档不再相关原因已记录

每张卡片应遵循此模式:

{
  "id": "agent-card-001",
  "title": "构建动态工作流技能",
  "owner": "codex",
  "state": "running",
  "branch": "product/dynamic-workflow-team-orchestration",
  "worktree": ".",
  "acceptance": [
    "技能存在",
    "测试覆盖所需概念",
    "内容产物包含视频和文章角度"
  ],
  "merge_gate": "lint、重点测试和目录检查通过",
  "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负责人和合并门控的工作项。
  2. 选择执行模式:单智能体、动态工作流模式、dmux/tmux、工作树扇出或外部桌面编排器。
  3. 分配边界:每张卡片一个负责人,明确文件范围,并且在没有集成者的情况下不允许重叠写入。
  4. 运行智能体:每个智能体编写证据和交接笔记,而不仅仅是代码。
  5. 按序审查:先测试,然后差异审查,接着是安全/风险检查,最后是内容/产品润色。
  6. 谨慎合并:一个集成者解决冲突并更新控制面板或状态产物。
  7. 提取可复用技能:如果卡片模式重复出现,将其推广到 skills/。

控制面板要求

一个好的团队编排控制面板应显示:

  • 活跃的工作项及其智能体看板状态。
  • 负责人、操控程序、分支、工作树和最后心跳。
  • 指向交接产物、测试、屏幕截图和 PR 的链接。
  • 按负责人和解除阻塞操作分组的阻塞项。
  • 基于门控而非直觉的合并准备状态。
  • 应成为共享技能的可复用工作流候选。

在操作者能回答以下问题之前,不要添加更多自动化:谁拥有这个?什么改变了?什么门控失败了?什么可以安全合并?

动态工作流兼容性

当卡片需要动态工作流模式时:

  • 将任务本地的操控程序置于卡片负责人之下。
  • 在卡片上存储输入和输出。
  • 在从“运行中”移动到“审查中”之前,需要一次评估。
  • 仅在重复使用后,才将操控程序推广为共享技能。

需注意的故障模式

  • 智能体混乱:许多智能体在运行,但没有负责人或合并门控。
  • 隐形工作:有用的输出仅存在于聊天记录中。
  • 看板形式主义:存在看板,但卡片没有验收标准。
  • 重叠写入:并行智能体在没有工作树的情况下编辑相同文件。
  • 无产品产物:过程产生文档,但没有可运行或可发布的表面。

输出标准

每次编排流程完成时,需提供:

  • 看板/卡片变更。
  • 已合并或待处理的分支。
  • 测试和评估证据。
  • 带有负责人和下一步行动的阻塞项。
  • 新的共享技能候选。

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/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code

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

affaan-m/everything-claude-code-conventions

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

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

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.

相关技能