team-arch-opt

团队架构优化

编排多 Agent 架构优化：分析代码库 → 制定重构计划 → 实施更改 → 验证改进 → 审查代码质量。

架构

Skill(skill="team-arch-opt", 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       v
                 [analyzer][designer][refactorer][validator][reviewer]

角色注册表

角色	路径	前缀	内循环
coordinator	roles/coordinator/role.md	—	—
analyzer	roles/analyzer/role.md	ANALYZE-*	false
designer	roles/designer/role.md	DESIGN-*	false
refactorer	roles/refactorer/role.md	REFACTOR-, FIX-	true
validator	roles/validator/role.md	VALIDATE-*	false
reviewer	roles/reviewer/role.md	REVIEW-, QUALITY-	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：TAO
• 会话路径：.workflow/.team/TAO-<slug>-<date>/
• 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>, ...)

Worker 启动模板

协调器使用此模板启动 worker：

Agent({
  subagent_type: "team-worker",
  description: "Spawn <role> worker",
  team_name: "arch-opt",
  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: arch-opt
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).`
})

内循环角色（refactorer）：动态设置 inner_loop — 单任务模式设为 true，扇出/独立（并行分支）模式设为 false。 单任务角色（analyzer、designer、validator、reviewer）：设置 inner_loop: false。

用户命令

命令	操作
check / status	查看执行状态图（按分支分组），不推进流程
resume / continue	检查 worker 状态，推进到下一步
revise <TASK-ID> [feedback]	修订指定任务并级联处理下游任务
feedback <text>	分析反馈影响，创建有针对性的修订链
recheck	重新运行质量检查
improve [dimension]	自动改进最薄弱的维度

会话目录

.workflow/.team/TAO-<slug>-<date>/
├── session.json                    # Session metadata + status + parallel_mode
├── task-analysis.json              # Coordinator analyze output
├── artifacts/
│   ├── architecture-baseline.json  # Analyzer: pre-refactoring metrics
│   ├── architecture-report.md      # Analyzer: ranked structural issue findings
│   ├── refactoring-plan.md         # Designer: prioritized refactoring plan
│   ├── validation-results.json     # Validator: post-refactoring validation
│   ├── review-report.md            # Reviewer: code review findings
│   ├── aggregate-results.json      # Fan-out/independent: aggregated results
│   ├── branches/                   # Fan-out mode branch artifacts
│   │   └── B{NN}/
│   │       ├── refactoring-detail.md
│   │       ├── validation-results.json
│   │       └── review-report.md
│   └── pipelines/                  # Independent mode pipeline artifacts
│       └── {P}/
│           └── ...
├── explorations/
│   ├── cache-index.json            # Shared explore cache
│   └── <hash>.md
├── wisdom/
│   └── patterns.md                 # Discovered patterns and conventions
├── discussions/
│   ├── DISCUSS-REFACTOR.md
│   └── DISCUSS-REVIEW.md
└── .msg/
    ├── messages.jsonl              # Message bus log
    └── meta.json                   # Session state + cross-role state

规格参考

• specs/pipelines.md — 流水线定义、任务注册表、并行模式

错误处理

场景	解决方法
未知命令	显示可用命令列表并报错
未找到角色	显示角色注册表并报错
CLI 工具失败	Worker 回退到直接实施
快速推进冲突	协调器在下一次回调时协调处理
完成操作失败	默认设为 Keep Active
consensus_blocked HIGH	协调器创建修订任务或暂停流水线
分支修复周期 >= 3	仅将该分支升级给用户处理，其他分支继续
max_branches 超出限制	协调器在 CP-2.5 截断到前 N 个分支