agentleFS
DrifterXXXDrifterXXX/auto-company/.agents/skills/team/SKILL.md

team

Skill0 starsChanged 5 months agoMITView on GitHub

根据任务快速组建临时 AI Agent 团队协作。自动从 .Codex/agents/ 中选择最合适的成员组队。

50 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ultraqa and ralplan.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Jurel89Skill

    ultraqa

    QA cycling loop — build/lint/test, fix, retry up to 5 cycles

    Also in 5 projects that use this

  • ibahgatSkill

    ralplan

    Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.

    Also in 9 projects that use this

The file

Files
SKILL.md

组建临时团队

你需要根据下面的任务,从公司现有的 AI Agent 中挑选最合适的成员,组建一支临时团队来协作完成。

任务

$ARGUMENTS

可用 Agent

以下是公司所有 Agent,定义在 .Codex/agents/ 目录下:

Agent文件职能
CEOceo-bezos战略决策、商业模式、PR/FAQ、优先级
CTOcto-vogels技术架构、技术选型、系统设计
逆向思考critic-munger质疑决策、识别致命缺陷、Pre-Mortem、防止集体幻觉
产品设计product-norman产品定义、用户体验、可用性
UI 设计ui-duarte视觉设计、设计系统、配色排版
交互设计interaction-cooper用户流程、Persona、交互模式
全栈开发fullstack-dhh代码实现、技术方案、开发
QAqa-bach测试策略、质量把控、Bug 分析
DevOps/SREdevops-hightower部署流水线、CI/CD、基础设施、监控运维
营销marketing-godin定位、品牌、获客、内容
运营operations-pg用户运营、增长、社区、PMF
销售sales-ross销售漏斗、转化策略
CFOcfo-campbell定价策略、财务模型、成本控制、单位经济
调研分析research-thompson市场调研、竞品分析、行业趋势、机会发现

执行步骤

1. 分析任务,选择成员

根据任务性质,选择 2-5 个最相关的 Agent 作为团队成员。选人原则:

  • 只选必要的:不是人越多越好,精准匹配任务需求
  • 考虑协作链:如果任务涉及从设计到开发,确保链路上的关键角色都在
  • 避免冗余:职能重叠的不要同时选

向创始人简要说明你选了谁、为什么选他们,然后立即开始组建。

2. 组建 Agent Team

使用 Agent Teams 功能组建临时团队:

  • 创建团队,team_name 基于任务简短命名(英文、kebab-case)
  • 为每个成员创建具体的任务(TaskCreate),任务描述要包含足够上下文
  • 用 Task 工具 spawn 每个 teammate,subagent_type 选 general-purpose,在 prompt 中注入对应 agent 文件的完整内容作为角色设定
  • spawn teammate 时通过 prompt 告知:你的角色设定、要完成的任务、产出文档存放在 docs/<role>/ 目录下

3. 协调与汇总

  • 作为 team lead 协调各成员工作
  • 收集各成员产出,汇总为统一的结论或方案
  • 如有分歧,列出各方观点供创始人决策
  • 完成后清理团队资源

注意事项

  • 所有沟通使用中文,技术术语保留英文
  • 每个成员产出的文档按约定存放在 docs/<role>/ 下
  • 团队是临时的,任务完成后即解散
  • 创始人是最终决策者,Agent 提供建议但不替代决策

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.