team-testing

团队测试

编排多 Agent 测试流水线：策略制定者 -> 生成器 -> 执行器 -> 分析师。逐步覆盖各层（L1/L2/L3），通过生成器-评审者循环实现覆盖率收敛。

架构

Skill(skill="team-testing", args="task description")
                    |
         SKILL.md (this file) = Router
                    |
     +--------------+--------------+
     |                             |
  no --role flag              --role <name>
     |                             |
  Coordinator                  Worker
  roles/coordinator/role.md    roles/<name>/role.md
     |
     +-- analyze -> dispatch -> spawn workers -> STOP
                                    |
                    +-------+-------+-------+-------+
                    v       v       v       v
                [strat] [gen]  [exec]  [analyst]
                team-worker agents, each loads roles/<role>/role.md

角色注册表

角色	路径	前缀	内部循环
协调者	roles/coordinator/role.md	—	—
策略制定者	roles/strategist/role.md	STRATEGY-*	false
生成器	roles/generator/role.md	TESTGEN-*	true
执行器	roles/executor/role.md	TESTRUN-*	dynamic
分析师	roles/analyst/role.md	TESTANA-*	false

角色路由器

解析 $ARGUMENTS：

• 包含 --role <name> -> 读取 roles/<name>/role.md，执行阶段 2-4
• 不包含 --role -> @roles/coordinator/role.md，执行入口路由器

共享常量

• 会话前缀：TST
• 会话路径：.workflow/.team/TST-<slug>-<date>/
• 团队名称：testing
• CLI 工具：ccw cli --mode analysis（只读），ccw cli --mode write（修改）
• 消息总线：mcp__ccw-tools__team_msg(session_id=<session-id>, ...)

工作线程启动模板

协调者使用此模板启动工作线程：

Agent({
  subagent_type: "team-worker",
  description: "Spawn <role> worker",
  team_name: "testing",
  name: "<role>",
  run_in_background: true,
  prompt: `## Role Assignment
role: <role>
role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: testing
requirement: <task-description>
inner_loop: <true|false>

## Progress Milestones
session_id: <session-id>
Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).
Report blockers immediately via team_msg type="blocker".
Report completion via team_msg type="task_complete" after final SendMessage.

Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
})

用户命令

命令	操作
check / status	查看流水线状态图
resume / continue	进入下一步
revise <TASK-ID>	修改指定任务
feedback <text>	注入反馈以进行修改

完成操作

流水线完成后，协调者将展示：

AskUserQuestion({
  questions: [{
    question: "Testing pipeline complete. What would you like to do?",
    header: "Completion",
    multiSelect: false,
    options: [
      { label: "Archive & Clean (Recommended)", description: "Archive session, clean up team" },
      { label: "Keep Active", description: "Keep session for follow-up work" },
      { label: "Deepen Coverage", description: "Add more test layers or increase coverage targets" }
    ]
  }]
})

会话目录

.workflow/.team/TST-<slug>-<date>/
├── .msg/messages.jsonl     # Team message bus
├── .msg/meta.json          # Session metadata
├── wisdom/                 # Cross-task knowledge
├── strategy/               # Strategist output
├── tests/                  # Generator output (L1-unit/, L2-integration/, L3-e2e/)
├── results/                # Executor output
└── analysis/               # Analyst output

规范参考

• specs/pipelines.md — 流水线定义和任务注册表
• specs/team-config.json — 团队配置

错误处理

场景	解决方案
未知的 --role 值	报错并列出可用角色
找不到角色	报错并显示预期路径（roles//role.md）
CLI 工具失败	工作线程回退到直接实现
GC 循环超限	发出警告并接受当前覆盖率
快速推进冲突	协调者在下次回调时协调处理
完成操作失败	默认设为保持活动状态