Communitygithub.com

团队构建器

交互式智能体选择器,用于组建并并行派遣团队。当你需要为某个任务组建并派遣一个并行智能体团队时使用。

团队构建器 是什么?

团队构建器是一个交互式菜单工具,帮助用户按需浏览、组建并派遣Agent团队。它支持扁平目录和领域子目录两种Agent文件组织方式,能够动态发现所有可用的Agent(包括用户自定义、插件和内置Agent),并自动推断其所属领域(如工程、营销、销售)。用户可以通过数字、名称或模糊匹配选择最多5个Agent,系统会并行启动所有选定Agent执行任务,最后汇总输出结果并生成综合报告,突出各Agent之间的意见一致、冲突以及后续建议。该技能适用于Claude Code等平台,利用并行Agent调用模式提升多Agent协作效率,避免硬编码Agent列表,确保新添加的Agent自动出现在菜单中。

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

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

团队构建器 是做什么的?

交互式菜单,用于按需浏览和组建智能体团队。支持扁平目录或领域子目录的智能体集合。

何时使用

  • 当你拥有多个智能体角色(markdown 文件)并希望为某个任务选择使用哪些智能体时
  • 当你希望从不同领域(例如:安全 + SEO + 架构)组成一个临时团队时
  • 当你希望在决定前先浏览可用的智能体时

前提条件

智能体文件必须是包含角色提示(身份、规则、工作流程、交付物)的 markdown 文件。第一个 # 标题 用作智能体名称,第一个段落用作描述。

支持扁平目录和子目录布局:

子目录布局 — 领域从文件夹名称推断:

agents/
├── engineering/
│   ├── security-engineer.md
│   └── software-architect.md
├── marketing/
│   └── seo-specialist.md
└── sales/
    └── discovery-coach.md

扁平布局 — 领域从共享文件名前缀推断。当前缀在2个或更多文件中共享时,该前缀被视为一个领域。具有唯一前缀的文件归入“通用”。注意:算法在第一个 - 处分割,因此多词领域(例如 product-management)应改用子目录布局:

agents/
├── engineering-security-engineer.md
├── engineering-software-architect.md
├── marketing-seo-specialist.md
├── marketing-content-strategist.md
├── sales-discovery-coach.md
└── sales-outbound-strategist.md

配置

通过两种方法发现智能体,按智能体名称进行合并和去重:

  1. claude agents 命令(主要)— 运行 claude agents 获取 CLI 已知的所有智能体,包括用户智能体、插件智能体(例如 ecc:architect)和内置智能体。这无需任何路径配置即可自动涵盖 ECC 市场安装。
  2. 文件 glob(备用,用于读取智能体内容)— 智能体 markdown 文件从以下路径读取:
    • ./agents/**/*.md + ./agents/*.md — 项目本地智能体
    • ~/.claude/agents/**/*.md + ~/.claude/agents/*.md — 全局用户智能体

当名称冲突时,较早的来源优先:用户智能体 > 插件智能体 > 内置智能体。如果用户指定了自定义路径,则可使用该路径替代。

工作原理

步骤 1:发现可用智能体

运行 claude agents 获取完整的智能体列表。解析每一行:

  • 插件智能体前缀为 plugin-name:(例如 ecc:security-reviewer)。使用 : 之后的部分作为智能体名称,插件名称作为领域。
  • 用户智能体没有前缀。从 ~/.claude/agents/ 或 ./agents/ 读取对应的 markdown 文件以提取名称和描述。
  • 内置智能体(例如 Explore、Plan)会被跳过,除非用户明确要求包含它们。

对于从 markdown 文件加载的用户智能体:

  • 子目录布局: 从父文件夹名称提取领域
  • 扁平布局: 收集所有文件名前缀(第一个 - 之前的文本)。只有当某个前缀出现在2个或更多文件名中时,它才被视为一个领域(例如 engineering-security-engineer.md 和 engineering-software-architect.md 都以 engineering 开头 → Engineering 领域)。具有唯一前缀的文件(例如 code-reviewer.md、tdd-guide.md)归入“通用”
  • 从第一个 # 标题 提取智能体名称。如果未找到标题,则从文件名派生名称(去掉 .md,将连字符替换为空格,首字母大写)
  • 从标题后的第一个段落提取一行摘要

如果在运行 claude agents 并探测文件位置后未找到任何智能体,请告知用户:“未找到智能体。请运行 claude agents 验证您的设置。”然后停止。

步骤 2:呈现领域菜单

可用智能体领域:
1. Engineering — Software Architect, Security Engineer
2. Marketing — SEO Specialist
3. Sales — Discovery Coach, Outbound Strategist

选择领域或指定具体智能体(例如 "1,3" 或 "security + seo"):
  • 跳过零个智能体的领域(空目录)
  • 显示每个领域的智能体数量

步骤 3:处理选择

接受灵活的输入:

  • 数字:"1,3" 选择 Engineering 和 Sales 中的所有智能体
  • 名称:"security + seo" 在已发现的智能体中进行模糊匹配
  • "all from engineering" 选择该领域中的每个智能体

如果选择了超过5个智能体,则按字母顺序列出它们并要求用户缩小范围:“您选择了N个智能体(最多5个)。请选择保留哪些,或说“first 5”以按字母顺序使用前五个。”

确认选择:

已选择:Security Engineer + SEO Specialist
他们应该处理什么任务?(描述任务):

步骤 4:并行启动智能体

  1. 读取每个选定智能体的 markdown 文件
  2. 如果尚未提供任务描述,则提示输入
  3. 使用 Agent 工具并行启动所有智能体:
    • subagent_type: "general-purpose"
    • prompt: "{智能体文件内容}\n\n任务:{任务描述}"
    • 每个智能体独立运行 — 无需智能体间通信
  4. 如果某个智能体失败(错误、超时或空输出),则内联记录失败信息(例如 “Security Engineer:失败 — [原因]”),并继续处理成功智能体的结果

步骤 5:综合结果

收集所有输出并呈现统一报告:

  • 按智能体分组的结果
  • 综合部分,突出显示:
    • 各智能体之间的一致意见
    • 各推荐之间的冲突或矛盾
    • 推荐的后续步骤

如果只选择了1个智能体,则跳过综合部分,直接呈现输出。

规则

  • 仅动态发现。 切勿硬编码智能体列表。目录中的新文件会自动出现在菜单中。
  • 每个团队最多5个智能体。 超过5个会产生收益递减和过多的 token 消耗。在选择时强制执行。
  • 并行派遣。 所有智能体同时运行 — 使用 Agent 工具的并行调用模式。
  • 并行 Agent 调用,而非 TeamCreate。 此技能使用并行 Agent 工具调用来完成独立工作。TeamCreate(Claude Code 中用于多智能体对话的工具)仅在智能体必须辩论或相互响应时才需要。

示例

用户:team builder

Claude:
可用智能体领域:
1. Engineering (2) — Software Architect, Security Engineer
2. Marketing (1) — SEO Specialist
3. Sales (4) — Discovery Coach, Outbound Strategist, Proposal Strategist, Sales Engineer
4. Support (1) — Executive Summary

选择领域或指定具体智能体:

用户:security + seo

Claude:
已选择:Security Engineer + SEO Specialist
他们应该处理什么任务?

用户:在启动前审查我的 Next.js 电商网站

[两个智能体并行启动,各自将专业知识应用于代码库]

Claude:
## Security Engineer 发现
- [发现...]

## SEO Specialist 发现
- [发现...]

## 综合
两个智能体一致认为:[...]
冲突:安全建议 CSP 阻止内联样式,SEO 需要内联 schema 标记。解决方案:[...]
后续步骤:[...]

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