‹ 首页

team-coordination

@karmaloopai · 收录于 1 周前

Coordinate software development work by analyzing requirements, delegating tasks to specialized sub-agents (developer, code-reviewer, tester), and synthesizing their work into cohesive deliverables. Use this for complex projects that require multiple specialized perspectives.

适合你,如果需要分解复杂项目并自动协调多个专业角色。

/ 下载安装
team-coordination.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add karmaloopai/jiva/team-coordination
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- karmaloopai/jiva/team-coordination
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify karmaloopai/jiva/team-coordination
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
35GitHub stars
~342上下文体积 · 单文件
镜像托管

怎么用

技能原文 SKILL.md作者撰写 · MIT · 12d1d33

Team Coordination Skill

Overview

Coordinate complex software engineering tasks by leveraging specialized team member personas.

Workflow
  1. Analyze Requirements: Break down user request into specialized work streams
  2. Delegate to Specialist: Spawn sub-agents with appropriate personas:
  3. developer: For implementation work
  4. code-reviewer: For code review and security analysis
  5. tester: For test creation and validation
  6. Coordinate Work: Ensure specialists have proper context and task clarity
  7. Integrate Results: Combine outputs from different specialists into final deliverable
  8. Report Status: Provide comprehensive summary to user
Available Team Members
  • developer: Implements features, fixes bugs, writes production code
  • code-reviewer: Reviews code for bugs, security issues, performance, style
  • tester: Creates unit tests, integration tests, validates functionality
Example Usage

When user says: "Build a user authentication system"

  1. Spawn developer to implement auth logic
  2. Spawn code-reviewer to review security
  3. Spawn tester to write comprehensive tests
  4. Integrate all their work into final deliverable
Best Practices
  • Give each specialist a clear, focused task
  • Provide sufficient context from user's original request
  • Don't spawn agents for trivial work you can do directly
  • Review specialist outputs before final delivery
  • Synthesize findings across specialists when multiple perspectives are valuable
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。