team-frontend

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Team Frontend Development

团队前端开发

Unified team skill: frontend development with built-in ui-ux-pro-max design intelligence. Covers requirement analysis, design system generation, frontend implementation, and quality assurance. All team members invoke with

--role=xxx

to route to role-specific execution.

统一团队Skill：集成ui-ux-pro-max设计智能能力的前端开发能力，覆盖需求分析、设计系统生成、前端实现及质量保障全流程。所有团队成员可通过

--role=xxx

参数调用，路由至对应角色的专属执行逻辑。

Architecture

架构

┌──────────────────────────────────────────────────────┐
│  Skill(skill="team-frontend")                         │
│  args="<task-description>" or args="--role=xxx"       │
└──────────────────────────┬───────────────────────────┘
                           │ Role Router
                ┌──── --role present? ────┐
                │ NO                      │ YES
                ↓                         ↓
         Orchestration Mode         Role Dispatch
         (auto -> coordinator)     (route to role.md)
                │
           ┌────┴────┬───────────┬───────────┬───────────┐
           ↓         ↓           ↓           ↓           ↓
      ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐
      │ coord  │ │analyst │ │architect│ │developer│ │  qa   │
      │        │ │ANALYZE-*│ │ARCH-*  │ │DEV-*   │ │QA-*   │
      └────────┘ └────────┘ └────────┘ └────────┘ └────────┘

┌──────────────────────────────────────────────────────┐
│  Skill(skill="team-frontend")                         │
│  args="<task-description>" or args="--role=xxx"       │
└──────────────────────────┬───────────────────────────┘
                           │ 角色路由
                ┌──── 是否存在--role? ────┐
                │ 否                      │ 是
                ↓                         ↓
         编排模式         角色分发
         (自动路由至coordinator)     (路由至role.md)
                │
           ┌────┴────┬───────────┬───────────┬───────────┐
           ↓         ↓           ↓           ↓           ↓
      ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐
      │ 协调者  │ │分析师 │ │架构师│ │开发人员│ │ 测试人员 │
      │        │ │ANALYZE-*│ │ARCH-*  │ │DEV-*   │ │QA-*   │
      └────────┘ └────────┘ └────────┘ └────────┘ └────────┘

Command Architecture

命令架构

Each role is organized as a folder with a

role.md

orchestrator and optional

commands/

for delegation:

roles/
├── coordinator/
│   ├── role.md
│   └── commands/
├── analyst/
│   ├── role.md
│   └── commands/
│       └── design-intelligence.md
├── architect/
│   ├── role.md
│   └── commands/
├── developer/
│   ├── role.md
│   └── commands/
└── qa/
    ├── role.md
    └── commands/
        └── pre-delivery-checklist.md

每个角色对应一个文件夹，包含一个

role.md

编排文件和可选的

commands/

目录用于任务委托：

roles/
├── coordinator/
│   ├── role.md
│   └── commands/
├── analyst/
│   ├── role.md
│   └── commands/
│       └── design-intelligence.md
├── architect/
│   ├── role.md
│   └── commands/
├── developer/
│   ├── role.md
│   └── commands/
└── qa/
    ├── role.md
    └── commands/
        └── pre-delivery-checklist.md

Role Router

角色路由

Input Parsing

输入解析

Parse

$ARGUMENTS

to extract

--role

. If absent -> Orchestration Mode (auto route to coordinator).

解析

$ARGUMENTS

提取

--role

参数。若未找到该参数，则进入编排模式（自动路由至coordinator）。

Role Registry

角色注册表

Role	File	Task Prefix	Type	Compact
coordinator	roles/coordinator/role.md	(none)	orchestrator	compressed -> must re-read
analyst	roles/analyst/role.md	ANALYZE-*	pipeline	compressed -> must re-read
architect	roles/architect/role.md	ARCH-*	pipeline	compressed -> must re-read
developer	roles/developer/role.md	DEV-*	pipeline	compressed -> must re-read
qa	roles/qa/role.md	QA-*	pipeline	compressed -> must re-read

COMPACT PROTECTION: Role files are execution documents, not reference material. When context compression occurs and role instructions are reduced to summaries, you MUST immediately
Read
the corresponding role.md to reload before continuing execution. Do not execute any Phase based on summaries.

角色	文件	任务前缀	类型	压缩状态
coordinator	roles/coordinator/role.md	（无）	编排器	已压缩 -> 必须重新读取
analyst	roles/analyst/role.md	ANALYZE-*	流水线	已压缩 -> 必须重新读取
architect	roles/architect/role.md	ARCH-*	流水线	已压缩 -> 必须重新读取
developer	roles/developer/role.md	DEV-*	流水线	已压缩 -> 必须重新读取
qa	roles/qa/role.md	QA-*	流水线	已压缩 -> 必须重新读取

压缩保护：角色文件是执行文档，而非参考资料。当上下文被压缩导致角色说明被简化为摘要时，你必须立即读取对应的role.md文件重新加载完整内容后，再继续执行。禁止基于摘要执行任何阶段的任务。

Dispatch

分发逻辑

Extract
```
--role
```
from arguments
If no
```
--role
```
-> route to coordinator (Orchestration Mode)
Look up role in registry -> Read the role file -> Execute its phases

从参数中提取
```
--role
```
若未找到
```
--role
```
，则路由至coordinator（编排模式）
在注册表中查找对应角色 -> 读取角色文件 -> 执行各阶段任务

Orchestration Mode

编排模式

When invoked without

--role

, coordinator auto-starts. User just provides task description.

Invocation:

Skill(skill="team-frontend", args="<task-description>")

Lifecycle:

User provides task description
  -> coordinator Phase 1-3: Requirement clarification + industry identification -> TeamCreate -> Create task chain
  -> coordinator Phase 4: spawn first batch workers (background) -> STOP
  -> Worker executes -> SendMessage callback -> coordinator advances next step
  -> Loop until pipeline complete -> Phase 5 report

User Commands (wake paused coordinator):

Command	Action
`check` / `status`	Output execution status graph, no advancement
`resume` / `continue`	Check worker states, advance next step

当调用时未携带

--role

参数，coordinator会自动启动，用户只需提供任务描述即可。

调用方式：

Skill(skill="team-frontend", args="<task-description>")

生命周期：

用户提供任务描述
  -> coordinator 阶段1-3：需求澄清 + 行业识别 -> TeamCreate -> 创建任务链
  -> coordinator 阶段4：启动第一批后台工作进程 -> 停止
  -> 工作进程执行任务 -> 发送SendMessage回调 -> coordinator推进至下一步
  -> 循环直至流水线完成 -> 阶段5生成报告

用户命令（唤醒暂停的coordinator）：

命令	操作
`check` / `status`	输出执行状态图，不推进任务
`resume` / `continue`	检查工作进程状态，推进至下一步

Shared Infrastructure

共享基础设施

The following templates apply to all worker roles. Each role.md only needs to write Phase 2-4 role-specific logic.

以下模板适用于所有工作角色。每个role.md只需编写阶段2-4的角色专属逻辑即可。

Worker Phase 1: Task Discovery (shared by all workers)

工作进程阶段1：任务发现（所有角色共享）

Every worker executes the same task discovery flow on startup:

Call
```
TaskList()
```
to get all tasks
Filter: subject matches this role's prefix + owner is this role + status is pending + blockedBy is empty
No tasks -> idle wait
Has tasks ->
```
TaskGet
```
for details ->
```
TaskUpdate
```
mark in_progress

Resume Artifact Check (prevent duplicate output after resume):

Check whether this task's output artifact already exists
Artifact complete -> skip to Phase 5 report completion
Artifact incomplete or missing -> normal Phase 2-4 execution

每个工作进程启动时都会执行相同的任务发现流程：

调用
```
TaskList()
```
获取所有任务
过滤条件：主题匹配当前角色的任务前缀 + 任务所有者为当前角色 + 状态为待处理 + 无前置依赖
无匹配任务 -> 进入空闲等待
有匹配任务 -> 调用
```
TaskGet
```
获取任务详情 -> 调用
```
TaskUpdate
```
标记为进行中

恢复工件检查（避免恢复后重复输出）：

检查该任务的输出工件是否已存在
工件已完整 -> 直接跳至阶段5报告完成
工件不完整或缺失 -> 正常执行阶段2-4

Worker Phase 5: Report (shared by all workers)

工作进程阶段5：报告（所有角色共享）

Standard reporting flow after task completion:

Message Bus: Call
```
mcp__ccw-tools__team_msg
```
to log message
- Parameters: operation="log", team=<session-id>, from=<role>, to="coordinator", type=<message-type>, summary="[<role>] <summary>", ref=<artifact-path>
- CLI fallback: When MCP unavailable ->
```
ccw team log --team <session-id> --from <role> --to coordinator --type <type> --summary "[<role>] ..." --json
```
- Note:
```
team
```
  must be session ID (e.g.,
```
FES-xxx-date
```
  ), NOT team name. Extract from
```
Session:
```
  field in task description.
SendMessage: Send result to coordinator (content and summary both prefixed with
```
[<role>]
```
)
TaskUpdate: Mark task completed
Loop: Return to Phase 1 to check next task

任务完成后的标准报告流程：

消息总线：调用
```
mcp__ccw-tools__team_msg
```
记录日志
- 参数：operation="log", team=<session-id>, from=<role>, to="coordinator", type=<message-type>, summary="[<role>] <摘要>", ref=<artifact-path>
- CLI降级方案：当MCP不可用时，执行
```
ccw team log --team <session-id> --from <role> --to coordinator --type <type> --summary "[<role>] ..." --json
```
- 注意：
```
team
```
  必须为会话ID（例如
```
FES-xxx-date
```
  ），而非团队名称。从任务描述的
```
Session:
```
  字段中提取。
SendMessage：向coordinator发送结果（内容和摘要均需添加
```
[<role>]
```
前缀）
TaskUpdate：标记任务为已完成
循环：返回阶段1检查下一个任务

Wisdom Accumulation (all roles)

智慧积累（所有角色）

Cross-task knowledge accumulation. Coordinator creates

wisdom/

directory at session initialization.

Directory:

<session-folder>/wisdom/
├── learnings.md      # Patterns and insights
├── decisions.md      # Architecture and design decisions
├── conventions.md    # Codebase conventions
└── issues.md         # Known risks and issues

Worker Load (Phase 2): Extract

Session: <path>

from task description, read wisdom directory files. Worker Contribute (Phase 4/5): Write this task's discoveries to corresponding wisdom files.

跨任务的知识积累机制。coordinator会在会话初始化时创建

wisdom/

目录。

目录结构：

<session-folder>/wisdom/
├── learnings.md      # 模式与洞察
├── decisions.md      # 架构与设计决策
├── conventions.md    # 代码库规范
└── issues.md         # 已知风险与问题

工作进程加载（阶段2）：从任务描述中提取

Session: <path>

，读取wisdom目录下的文件。 工作进程贡献（阶段4/5）：将当前任务的发现写入对应的wisdom文件。

Role Isolation Rules

角色隔离规则

Output Tagging

输出标记

All outputs must carry

[role_name]

prefix.

所有输出必须添加

[role_name]

前缀。

Coordinator Isolation

Coordinator隔离规则

Allowed	Forbidden
Requirement clarification (AskUserQuestion)	Direct code writing/modification
Create task chain (TaskCreate)	Calling implementation subagents
Dispatch tasks to workers	Direct analysis/testing/review
Monitor progress (message bus)	Bypassing workers
Report results to user	Modifying source code

允许操作	禁止操作
需求澄清（调用AskUserQuestion）	直接编写/修改代码
创建任务链（调用TaskCreate）	调用实现类子Agent
向工作进程分发任务	直接进行分析/测试/评审
通过消息总线监控进度	绕过工作进程执行任务
向用户报告结果	修改源代码

Worker Isolation

工作进程隔离规则

Allowed	Forbidden
Process tasks with own prefix	Process tasks with other role prefixes
SendMessage to coordinator	Communicate directly with other workers
Use tools declared in Toolbox	Create tasks for other roles (TaskCreate)
Delegate to commands/ files	Modify resources outside own responsibility

允许操作	禁止操作
处理带有自身前缀的任务	处理带有其他角色前缀的任务
向coordinator发送SendMessage	直接与其他工作进程通信
使用Toolbox中声明的工具	为其他角色创建任务（调用TaskCreate）
委托任务至commands/目录下的文件	修改自身职责范围外的资源

Message Bus (All Roles)

消息总线（所有角色）

Every SendMessage before, must call

mcp__ccw-tools__team_msg

to log.

Message types by role:

Role	Types
coordinator	`task_unblocked` , `sync_checkpoint` , `fix_required` , `error` , `shutdown`
analyst	`analyze_ready` , `analyze_progress` , `error`
architect	`arch_ready` , `arch_revision` , `arch_progress` , `error`
developer	`dev_complete` , `dev_progress` , `error`
qa	`qa_passed` , `qa_result` , `fix_required` , `error`

每次发送SendMessage 之前，必须调用

mcp__ccw-tools__team_msg

记录日志。

各角色对应的消息类型：

角色	消息类型
coordinator	`task_unblocked` , `sync_checkpoint` , `fix_required` , `error` , `shutdown`
analyst	`analyze_ready` , `analyze_progress` , `error`
architect	`arch_ready` , `arch_revision` , `arch_progress` , `error`
developer	`dev_complete` , `dev_progress` , `error`
qa	`qa_passed` , `qa_result` , `fix_required` , `error`

Shared Memory

共享内存

Cross-role accumulated knowledge stored in

shared-memory.json

Field	Owner	Content
`design_intelligence`	analyst	ui-ux-pro-max output
`design_token_registry`	architect	colors, typography, spacing, shadows
`component_inventory`	architect	Component specs
`style_decisions`	architect	Design system decisions
`qa_history`	qa	QA audit results
`industry_context`	analyst	Industry-specific rules

Each role reads in Phase 2, writes own fields in Phase 5.

跨角色积累的知识存储在

shared-memory.json

中：

字段	所有者	内容
`design_intelligence`	analyst	ui-ux-pro-max输出结果
`design_token_registry`	architect	颜色、排版、间距、阴影规范
`component_inventory`	architect	组件规格
`style_decisions`	architect	设计系统决策
`qa_history`	qa	QA审计结果
`industry_context`	analyst	行业特定规则

每个角色在阶段2读取数据，在阶段5写入自身负责的字段。

Pipeline Architecture

流水线架构

Three Pipeline Modes

三种流水线模式

page (single page - linear):
  ANALYZE-001 -> ARCH-001 -> DEV-001 -> QA-001

feature (multi-component feature - with architecture review):
  ANALYZE-001 -> ARCH-001(tokens+structure) -> QA-001(architecture-review)
  -> DEV-001(components) -> QA-002(code-review)

system (full frontend system - dual-track parallel):
  ANALYZE-001 -> ARCH-001(tokens) -> QA-001(token-review)
  -> [ARCH-002(components) || DEV-001(tokens)](parallel, blockedBy QA-001)
  -> QA-002(component-review) -> DEV-002(components) -> QA-003(final)

页面模式（单页面 - 线性执行）：
  ANALYZE-001 -> ARCH-001 -> DEV-001 -> QA-001

功能模式（多组件功能 - 含架构评审）：
  ANALYZE-001 -> ARCH-001(令牌+结构) -> QA-001(架构评审)
  -> DEV-001(组件) -> QA-002(代码评审)

系统模式（完整前端系统 - 双轨并行）：
  ANALYZE-001 -> ARCH-001(令牌) -> QA-001(令牌评审)
  -> [ARCH-002(组件) || DEV-001(令牌)](并行执行，依赖QA-001完成)
  -> QA-002(组件评审) -> DEV-002(组件) -> QA-003(最终检查)

Generator-Critic Loop (developer <-> qa)

生成-评审循环（developer <-> qa）

Developer and qa iterate to ensure code quality and design compliance:

┌──────────┐     DEV artifact        ┌──────────┐
│ developer│ ─────────────────────>  │    qa    │
│(Generator)│                        │ (Critic) │
│          │  <───────────────────── │          │
└──────────┘   QA feedback           └──────────┘
               (max 2 rounds)

Convergence: qa.score >= 8 && qa.critical_count === 0

开发人员与测试人员通过迭代确保代码质量与设计合规性：

┌──────────┐     开发工件        ┌──────────┐
│ developer│ ─────────────────────>  │    qa    │
│(生成者)│                        │ (评审者) │
│          │  <───────────────────── │          │
└──────────┘   QA反馈           └──────────┘
               (最多2轮迭代)

收敛条件：qa.score >= 8 且 qa.critical_count === 0

Consulting Pattern (developer -> analyst)

咨询模式（developer -> analyst）

Developer can request design decision consultation via coordinator:

developer -> coordinator: "Need design decision consultation"
coordinator -> analyst: Create ANALYZE-consult task
analyst -> coordinator: Design recommendation
coordinator -> developer: Forward recommendation

开发人员可通过coordinator请求设计决策咨询：

developer -> coordinator: "需要设计决策咨询"
coordinator -> analyst: 创建ANALYZE-consult任务
analyst -> coordinator: 提供设计建议
coordinator -> developer: 转发建议

Cadence Control

节奏控制

Beat model: Event-driven, each beat = coordinator wake -> process -> spawn -> STOP.

Beat Cycle (single beat)
═══════════════════════════════════════════════════════════
  Event                   Coordinator              Workers
───────────────────────────────────────────────────────────
  callback/resume ──> ┌─ handleCallback ─┐
                      │  mark completed   │
                      │  check pipeline   │
                      ├─ handleSpawnNext ─┤
                      │  find ready tasks │
                      │  spawn workers ───┼──> [Worker A] Phase 1-5
                      │  (parallel OK)  ──┼──> [Worker B] Phase 1-5
                      └─ STOP (idle) ─────┘         │
                                                     │
  callback <─────────────────────────────────────────┘
  (next beat)              SendMessage + TaskUpdate(completed)
═══════════════════════════════════════════════════════════

Pipeline beat view:

Page mode (4 beats, strictly serial)
──────────────────────────────────────────────────────────
Beat  1         2         3         4
      │         │         │         │
      ANALYZE -> ARCH -> DEV -> QA
      ▲                            ▲
   pipeline                     pipeline
    start                        done

A=ANALYZE  ARCH=architect  D=DEV  Q=QA

Feature mode (5 beats, with architecture review gate)
──────────────────────────────────────────────────────────
Beat  1         2         3         4         5
      │         │         │         │         │
      ANALYZE -> ARCH -> QA-1 -> DEV -> QA-2
                          ▲               ▲
                   arch review      code review

System mode (7 beats, dual-track parallel)
──────────────────────────────────────────────────────────
Beat  1         2       3       4              5       6       7
      │         │       │  ┌────┴────┐         │       │       │
      ANALYZE -> ARCH-1 -> QA-1 -> ARCH-2 || DEV-1 -> QA-2 -> DEV-2 -> QA-3
                                   ▲                              ▲
                              parallel window                 final check

Checkpoints:

Trigger	Location	Behavior
Architecture review gate	QA-001 (arch review) complete	Pause if critical issues, wait for architect revision
GC loop limit	developer <-> qa max 2 rounds	Exceed rounds -> stop iteration, report current state
Pipeline stall	No ready + no running	Check missing tasks, report to user

Stall Detection (coordinator

handleCheck

executes):

Check	Condition	Resolution
Worker no response	in_progress task no callback	Report waiting task list, suggest user `resume`
Pipeline deadlock	no ready + no running + has pending	Check blockedBy dependency chain, report blocking point
GC loop exceeded	DEV/QA iteration > max_rounds	Terminate loop, output latest QA report

节拍模型：事件驱动，每个节拍 = coordinator唤醒 -> 处理任务 -> 启动工作进程 -> 停止。

节拍周期（单个节拍）
═══════════════════════════════════════════════════════════
  事件                   Coordinator              工作进程
───────────────────────────────────────────────────────────
  回调/恢复 ──> ┌─ 处理回调 ─┐
                │  标记任务完成   │
                │  检查流水线状态   │
                ├─ 启动下一批任务 ─┤
                │  查找可执行任务 │
                │  启动工作进程 ───┼──> [工作进程A] 阶段1-5
                │  （支持并行）  ──┼──> [工作进程B] 阶段1-5
                └─ 停止（空闲） ─────┘         │
                                                     │
  回调 <─────────────────────────────────────────┘
  (下一个节拍)              发送SendMessage + TaskUpdate(已完成)
═══════════════════════════════════════════════════════════

流水线节拍视图：

页面模式（4个节拍，严格串行）
──────────────────────────────────────────────────────────
节拍  1         2         3         4
      │         │         │         │
      ANALYZE -> ARCH -> DEV -> QA
      ▲                            ▲
   流水线启动                     流水线完成

A=ANALYZE  ARCH=architect  D=DEV  Q=QA

功能模式（5个节拍，含架构评审关卡）
──────────────────────────────────────────────────────────
节拍  1         2         3         4         5
      │         │         │         │         │
      ANALYZE -> ARCH -> QA-1 -> DEV -> QA-2
                          ▲               ▲
                   架构评审      代码评审

系统模式（7个节拍，双轨并行）
──────────────────────────────────────────────────────────
节拍  1         2       3       4              5       6       7
      │         │       │  ┌────┴────┐         │       │       │
      ANALYZE -> ARCH-1 -> QA-1 -> ARCH-2 || DEV-1 -> QA-2 -> DEV-2 -> QA-3
                                   ▲                              ▲
                              并行执行窗口                 最终检查

检查点：

触发条件	位置	行为
架构评审关卡	QA-001（架构评审）完成	若存在关键问题则暂停，等待架构师修订
生成-评审循环次数上限	developer与qa迭代超过2轮	超出次数后终止循环，报告当前状态
流水线停滞	无可执行任务且无运行中任务	检查缺失任务，向用户报告

停滞检测（coordinator执行

handleCheck

）：

检查项	触发条件	解决方案
工作进程无响应	标记为进行中的任务未回调	报告等待中的任务列表，建议用户执行 `resume`
流水线死锁	无可执行任务、无运行中任务但有待处理任务	检查blockedBy依赖链，报告阻塞点
生成-评审循环超限	DEV/QA迭代次数超过上限	终止循环，输出最新QA报告

Task Metadata Registry

任务元数据注册表

Task ID	Role	Phase	Dependencies	Description
ANALYZE-001	analyst	analysis	(none)	Requirement analysis + design intelligence via ui-ux-pro-max
ARCH-001	architect	design	ANALYZE-001	Design token system + component architecture
ARCH-002	architect	design	QA-001 (system mode)	Component specs refinement
DEV-001	developer	impl	ARCH-001 or QA-001	Frontend component/page implementation
DEV-002	developer	impl	QA-002 (system mode)	Component implementation from refined specs
QA-001	qa	review	ARCH-001 or DEV-001	Architecture review or code review
QA-002	qa	review	DEV-001	Code review (feature/system mode)
QA-003	qa	review	DEV-002 (system mode)	Final quality check

任务ID	角色	阶段	依赖	描述
ANALYZE-001	analyst	分析	（无）	需求分析 + 通过ui-ux-pro-max获取设计智能
ARCH-001	architect	设计	ANALYZE-001	设计令牌系统 + 组件架构
ARCH-002	architect	设计	QA-001（系统模式）	组件规格细化
DEV-001	developer	实现	ARCH-001或QA-001	前端组件/页面实现
DEV-002	developer	实现	QA-002（系统模式）	基于细化规格的组件实现
QA-001	qa	评审	ARCH-001或DEV-001	架构评审或代码评审
QA-002	qa	评审	DEV-001	代码评审（功能/系统模式）
QA-003	qa	评审	DEV-002（系统模式）	最终质量检查

Coordinator Spawn Template

Coordinator启动模板

When coordinator spawns workers, use background mode (Spawn-and-Stop):

Task({
  subagent_type: "general-purpose",
  description: "Spawn <role> worker",
  team_name: <team-name>,
  name: "<role>",
  run_in_background: true,
  prompt: `You are team "<team-name>" <ROLE>.

当coordinator启动工作进程时，需使用后台模式（启动后停止）：

Task({
  subagent_type: "general-purpose",
  description: "Spawn <role> worker",
  team_name: <team-name>,
  name: "<role>",
  run_in_background: true,
  prompt: `你是团队"<team-name>"的<ROLE>。

Primary Directive

核心指令

All your work must be executed through Skill to load role definition: Skill(skill="team-frontend", args="--role=<role>")

Current requirement: <task-description> Session: <session-folder>

所有工作必须通过Skill加载角色定义后执行： Skill(skill="team-frontend", args="--role=<role>")

当前需求：<task-description> 会话：<session-folder>

Role Guidelines

角色准则

Only process <PREFIX>-* tasks, do not execute other role work
All output prefixed with [<role>] identifier
Only communicate with coordinator
Do not use TaskCreate for other roles
Call mcp__ccw-tools__team_msg before every SendMessage

仅处理<PREFIX>-*前缀的任务，禁止执行其他角色的工作
所有输出需添加[<role>]标识前缀
仅与coordinator通信
禁止为其他角色创建任务（调用TaskCreate）
每次发送SendMessage前必须调用mcp__ccw-tools__team_msg

Workflow

工作流程

Call Skill -> load role definition and execution logic
Follow role.md 5-Phase flow
team_msg + SendMessage results to coordinator
TaskUpdate completed -> check next task` })

undefined

调用Skill -> 加载角色定义与执行逻辑
遵循role.md的5阶段流程执行
调用team_msg并通过SendMessage向coordinator发送结果
调用TaskUpdate标记任务完成 -> 检查下一个任务` })

undefined

ui-ux-pro-max Integration

ui-ux-pro-max集成

Design Intelligence Engine

设计智能引擎

Analyst role invokes ui-ux-pro-max via Skill to obtain industry design intelligence:

Action	Invocation
Full design system recommendation	`Skill(skill="ui-ux-pro-max", args="<industry> <keywords> --design-system")`
Domain search (UX, typography, color)	`Skill(skill="ui-ux-pro-max", args="<query> --domain <domain>")`
Tech stack guidance	`Skill(skill="ui-ux-pro-max", args="<query> --stack <stack>")`
Persist design system (cross-session)	`Skill(skill="ui-ux-pro-max", args="<query> --design-system --persist -p <projectName>")`

Supported Domains: product, style, typography, color, landing, chart, ux, web Supported Stacks: html-tailwind, react, nextjs, vue, svelte, shadcn, swiftui, react-native, flutter

Fallback: If ui-ux-pro-max skill not installed, degrade to LLM general design knowledge. Suggest installation:

/plugin install ui-ux-pro-max@ui-ux-pro-max-skill

分析师角色通过Skill调用ui-ux-pro-max获取行业设计智能：

操作	调用方式
完整设计系统推荐	`Skill(skill="ui-ux-pro-max", args="<industry> <keywords> --design-system")`
领域搜索（UX、排版、颜色）	`Skill(skill="ui-ux-pro-max", args="<query> --domain <domain>")`
技术栈指导	`Skill(skill="ui-ux-pro-max", args="<query> --stack <stack>")`
持久化设计系统（跨会话）	`Skill(skill="ui-ux-pro-max", args="<query> --design-system --persist -p <projectName>")`

支持的领域：product, style, typography, color, landing, chart, ux, web 支持的技术栈：html-tailwind, react, nextjs, vue, svelte, shadcn, swiftui, react-native, flutter

降级方案：若未安装ui-ux-pro-max Skill，则降级为使用LLM通用设计知识。同时建议执行安装命令：

/plugin install ui-ux-pro-max@ui-ux-pro-max-skill

Session Directory

会话目录

.workflow/.team/FE-<slug>-<YYYY-MM-DD>/
├── team-session.json           # Session state
├── shared-memory.json          # Cross-role accumulated knowledge
├── wisdom/                     # Cross-task knowledge
│   ├── learnings.md
│   ├── decisions.md
│   ├── conventions.md
│   └── issues.md
├── analysis/                   # Analyst output
│   ├── design-intelligence.json
│   └── requirements.md
├── architecture/               # Architect output
│   ├── design-tokens.json
│   ├── component-specs/
│   │   └── <component-name>.md
│   └── project-structure.md
├── qa/                         # QA output
│   └── audit-<NNN>.md
└── build/                      # Developer output
    ├── token-files/
    └── component-files/

.workflow/.team/FE-<slug>-<YYYY-MM-DD>/
├── team-session.json           # 会话状态
├── shared-memory.json          # 跨角色积累的知识
├── wisdom/                     # 跨任务知识
│   ├── learnings.md
│   ├── decisions.md
│   ├── conventions.md
│   └── issues.md
├── analysis/                   # 分析师输出
│   ├── design-intelligence.json
│   └── requirements.md
├── architecture/               # 架构师输出
│   ├── design-tokens.json
│   ├── component-specs/
│   │   └── <component-name>.md
│   └── project-structure.md
├── qa/                         # QA输出
│   └── audit-<NNN>.md
└── build/                      # 开发人员输出
    ├── token-files/
    └── component-files/

Error Handling

错误处理

Scenario	Resolution
Unknown --role value	Error with available role list
Missing --role arg	Orchestration Mode -> auto route to coordinator
Role file not found	Error with expected path (roles/<name>/role.md)
QA score < 6 over 2 GC rounds	Coordinator reports to user
Dual-track sync failure	Fallback to single-track sequential execution
ui-ux-pro-max skill not installed	Degrade to LLM general design knowledge, show install command
DEV cannot find design files	Wait for sync point or escalate to coordinator

场景	解决方案
未知--role参数值	返回错误信息并列出可用角色
缺失--role参数	进入编排模式 -> 自动路由至coordinator
角色文件未找到	返回错误信息并给出预期路径（roles/<name>/role.md）
2轮生成-评审循环后QA评分<6	Coordinator向用户报告该情况
双轨同步失败	降级为单轨串行执行
未安装ui-ux-pro-max Skill	降级为使用LLM通用设计知识，同时显示安装命令
DEV无法找到设计文件	等待同步点或向coordinator上报

undefined