brainstorming

将创意构思为设计方案

通过智能选择 Agent 和结构化探索，将粗略想法转化为完整的设计方案。

**核心原则：**分析主题，动态选择相关 Agent，并行探索备选方案，逐步呈现设计。

参数解析

TOPIC = "$ARGUMENTS"  # Full argument string, e.g., "API design for payments"
# $ARGUMENTS[0] is the first token (CC 2.1.59 indexed access)

---

步骤 0：发现项目上下文

创建任务或选择 Agent 之前，先检测项目层级。该层级将成为所有后续决策的复杂度上限。

自动检测（扫描代码库）

# PARALLEL — quick signals (launch all in ONE message)
Grep(pattern="take-home|assignment|interview|hackathon", glob="README*", output_mode="content")
Grep(pattern="take-home|assignment|interview|hackathon", glob="*.md", output_mode="content")
Glob(pattern=".github/workflows/*")
Glob(pattern="**/Dockerfile")
Glob(pattern="**/terraform/**")
Glob(pattern="**/k8s/**")
Glob(pattern="CONTRIBUTING.md")

层级分类

信号	层级
README 写有“take-home”“assignment”或时间限制	1. 面试
文件少于 10 个，没有 CI，也没有 Docker	2. 黑客松
有 .github/workflows/，依赖项为 10-25 个	3. MVP
有模块边界、Redis、后台任务	4. 成长阶段
有 K8s/Terraform、DDD 结构、monorepo	5. 企业级
有 CONTRIBUTING.md、LICENSE，依赖项极少	6. 开源

如果置信度较低，请询问用户：

AskUserQuestion(questions=[{
  "question": "What kind of project is this?",
  "header": "Project tier",
  "options": [
    {"label": "Interview / take-home", "description": "8-15 files, 200-600 LOC, simple architecture", "markdown": "```\nTier 1: Interview / Take-Home\n─────────────────────────────\nFiles:    8-15 max\nLOC:      200-600\nArch:     Flat structure, no abstractions\nPatterns: Direct imports, inline logic\nTests:    Unit only, co-located\n```"},
    {"label": "Startup / MVP", "description": "MVC monolith, managed services, ship fast", "markdown": "```\nTier 3: Startup / MVP\n─────────────────────\nArch:     MVC monolith\nDB:       Managed (RDS/Supabase)\nCI:       GitHub Actions (1-2 workflows)\nPatterns: Service layer, repository pattern\nDeploy:   Vercel / Railway / Fly.io\n```"},
    {"label": "Growth / enterprise", "description": "Modular monolith or DDD, full observability", "markdown": "```\nTier 4-5: Growth / Enterprise\n─────────────────────────────\nArch:     Modular monolith or DDD\nInfra:    K8s, Terraform, Redis, queues\nCI:       Multi-stage pipelines\nPatterns: Hexagonal, CQRS, event-driven\nObserve:  Structured logging, tracing\n```"},
    {"label": "Open source library", "description": "Minimal API surface, exhaustive tests", "markdown": "```\nTier 6: Open Source Library\n──────────────────────────\nAPI:      Minimal public surface\nTests:    100% coverage, property-based\nDocs:     README, API docs, examples\nCI:       Matrix builds, release automation\nPatterns: Semver, CONTRIBUTING.md\n```"}
  ],
  "multiSelect": false
}])

**将检测到的层级作为上下文传递给所有后续 Agent 和阶段。**层级会限制适用的模式——完整矩阵请参见 scope-appropriate-architecture 技能。

**覆盖：**用户始终可以覆盖检测到的层级。如果用户选择的层级高于检测结果，请提醒其注意权衡。

---

步骤 0a：使用 AskUserQuestion 确认用户意图

明确头脑风暴的约束：

AskUserQuestion(
  questions=[
    {
      "question": "What type of design exploration?",
      "header": "Type",
      "options": [
        {"label": "Open exploration (Recommended)", "description": "Generate 10+ ideas, evaluate all, synthesize top 3", "markdown": "```\nOpen Exploration (7 phases)\n──────────────────────────\n  Diverge        Evaluate       Synthesize\n  ┌─────┐       ┌─────┐       ┌─────┐\n  │ 10+ │──────▶│Rate │──────▶│Top 3│\n  │ideas│       │0-10 │       │picks│\n  └─────┘       └─────┘       └─────┘\n  3-5 agents    Devil's        Trade-off\n  in parallel   advocate       table\n```"},
        {"label": "Constrained design", "description": "I have specific requirements to work within", "markdown": "```\nConstrained Design\n──────────────────\n  Requirements ──▶ Feasibility ──▶ Design\n  ┌──────────┐    ┌──────────┐    ┌──────┐\n  │ Fixed    │    │ Check    │    │ Best │\n  │ bounds   │    │ fit      │    │ fit  │\n  └──────────┘    └──────────┘    └──────┘\n  Skip divergent phase, focus on\n  feasibility within constraints\n```"},
        {"label": "Comparison", "description": "Compare 2-3 specific approaches I have in mind", "markdown": "```\nComparison Mode\n───────────────\n  Approach A ──┐\n  Approach B ──┼──▶ Rate 0-10 ──▶ Winner\n  Approach C ──┘    (6 dims)\n\n  Skip ideation, jump straight\n  to evaluation + trade-off table\n```"},
        {"label": "Quick ideation", "description": "Generate ideas fast, skip deep evaluation", "markdown": "```\nQuick Ideation\n──────────────\n  Braindump ──▶ Light filter ──▶ List\n  ┌────────┐   ┌────────────┐   ┌────┐\n  │ 10+    │   │ Viable?    │   │ 5-7│\n  │ ideas  │   │ Y/N only   │   │ out│\n  └────────┘   └────────────┘   └────┘\n  Fast pass, no deep scoring\n```"},
        {"label": "Plan first", "description": "Structured exploration before generating ideas", "markdown": "```\nPlan Mode Exploration\n─────────────────────\n  1. EnterPlanMode\n  2. Analyze constraints\n  3. Research precedents\n  4. Map solution space\n  5. ExitPlanMode → options\n  6. User picks direction\n  7. Deep dive on chosen path\n\n  Best for: Architecture,\n  design systems, trade-offs\n```"}
      ],
      "multiSelect": false
    },
    {
      "question": "Any preferences or constraints?",
      "header": "Constraints",
      "options": [
        {"label": "None", "description": "Explore all possibilities"},
        {"label": "Use existing patterns", "description": "Prefer patterns already in codebase"},
        {"label": "Minimize complexity", "description": "Favor simpler solutions"},
        {"label": "I'll specify", "description": "Let me provide specific constraints"}
      ],
      "multiSelect": false
    }
  ]
)

**如果选择“先制定计划”：**调用 EnterPlanMode，仅使用 Read/Grep/Glob 进行研究，然后通过 ExitPlanMode 提交计划，待用户批准后再继续。

根据回答调整工作流：

• 开放探索：执行完整的 7 阶段流程，使用所有 Agent
• 受限设计：跳过发散阶段，重点关注可行性
• 方案比较：跳过创意构思，直接进入评估阶段
• 快速构思：生成创意，跳过深入评估

---

步骤 0b：选择编排模式（第 1-2 层级跳过）

选择 Agent Teams（网状模式——Agent 讨论并挑战创意）或 Task tool（星型模式——所有 Agent 向负责人汇报）：

1. CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 → Agent Teams 模式
2. Agent Teams 不可用 → Task tool 模式（默认）
3. 否则：开放探索且使用 3 个以上 Agent → 建议使用 Agent Teams（实时讨论能产生更好的创意）；快速构思 → Task tool

方面	Task Tool	Agent Teams
创意生成	每个 Agent 独立生成	Agent 相互启发创意
反方论证	所有 Agent 完成后由负责人提出质疑	Agent 实时相互质疑
成本	约 150K 个 token	约 400K 个 token
最适合	快速构思、受限设计	开放探索、深入评估

**备用方案：**如果 Agent Teams 遇到问题，剩余阶段改用 Task tool。

---

关键：任务管理是强制要求（CC 2.1.16）

# Create main task IMMEDIATELY
TaskCreate(
  subject="Brainstorm: {topic}",
  description="Design exploration with parallel agent research",
  activeForm="Brainstorming {topic}"
)

# Create subtasks for each phase
TaskCreate(subject="Analyze topic and select agents", activeForm="Analyzing topic")
TaskCreate(subject="Search memory for past decisions", activeForm="Searching knowledge graph")
TaskCreate(subject="Generate divergent ideas (10+)", activeForm="Generating ideas")
TaskCreate(subject="Feasibility fast-check", activeForm="Checking feasibility")
TaskCreate(subject="Evaluate with devil's advocate", activeForm="Evaluating ideas")
TaskCreate(subject="Synthesize top approaches", activeForm="Synthesizing approaches")
TaskCreate(subject="Present design options", activeForm="Presenting options")

---

七阶段流程

阶段	活动	输出
0. 主题分析	对关键词分类，选择 3-5 个 Agent	Agent 列表
1. 记忆 + 上下文	搜索图谱，检查代码库	既有模式
2. 发散探索	生成 10 个以上创意，不要筛选	创意池
3. 可行性快速检查	每个创意进行 30 秒可行性检查，包括可测试性	筛选后的创意
4. 评估与评分	按 0-10 分评分（6 个维度，含可测试性），进行反方论证	排名后的创意
5. 综合整理	筛选出前 2-3 个创意，制作权衡表，为每种方案制定测试策略	备选方案
6. 设计方案呈现	分成 200-300 字的小节呈现，包含测试计划	经验证的设计方案

加载阶段工作流以查看详细说明：

Read("${CLAUDE_PLUGIN_ROOT}/skills/brainstorming/references/phase-workflow.md")

---

不适用场景

以下情况请跳过头脑风暴：

• 需求非常清晰且具体
• 只有一种显而易见的方案
• 用户已经设计好解决方案
• 时间紧迫的 Bug 修复或紧急问题

---

快速参考：Agent 选择

主题示例	启动的 Agent
“为用户构思 API”	workflow-architect、backend-system-architect、security-auditor、test-generator
“构思仪表板 UI”	workflow-architect、frontend-ui-developer、test-generator
“构思 RAG 流水线”	workflow-architect、llm-integrator、data-pipeline-engineer、test-generator
“构思缓存策略”	workflow-architect、backend-system-architect、frontend-performance-engineer、test-generator

始终包含： workflow-architect，以获得系统设计视角；test-generator，以评估可测试性。

---

Agent Teams 替代方案：头脑风暴团队

在 Agent Teams 模式下，组建一个头脑风暴团队，让 Agent 实时讨论创意。根据主题分析动态选择队友（第 0 阶段）：

TeamCreate(team_name="brainstorm-{topic-slug}", description="Brainstorm {topic}")

# Always include the system design lead
Agent(subagent_type="workflow-architect", name="system-designer",
     team_name="brainstorm-{topic-slug}",
     prompt="""You are the system design lead for brainstorming: {topic}
     DIVERGENT MODE: Generate 3-4 architectural approaches.
     When other teammates share ideas, build on them or propose alternatives.
     Challenge ideas that seem over-engineered — advocate for simplicity.
     After divergent phase, help synthesize the top approaches.""")

# Domain-specific teammates (select 2-3 based on topic keywords)
Agent(subagent_type="backend-system-architect", name="backend-thinker",
     team_name="brainstorm-{topic-slug}",
     prompt="""Brainstorm backend approaches for: {topic}
     DIVERGENT MODE: Generate 3-4 backend-specific ideas.
     When system-designer shares architectural ideas, propose concrete API designs.
     Challenge ideas from other teammates with implementation reality checks.
     Play devil's advocate on complexity vs simplicity trade-offs.""")

Agent(subagent_type="frontend-ui-developer", name="frontend-thinker",
     team_name="brainstorm-{topic-slug}",
     prompt="""Brainstorm frontend approaches for: {topic}
     DIVERGENT MODE: Generate 3-4 UI/UX ideas.
     When backend-thinker proposes APIs, suggest frontend patterns that match.
     Challenge backend proposals that create poor user experiences.
     Advocate for progressive disclosure and accessibility.""")

# Always include: testability assessor
Agent(subagent_type="test-generator", name="testability-assessor",
     team_name="brainstorm-{topic-slug}",
     prompt="""Assess testability for each brainstormed approach: {topic}
     For every idea shared by teammates, evaluate:
     - Can core logic be unit tested without external services?
     - What's the mock/stub surface area?
     - Can it be integration-tested with docker-compose/testcontainers?
     Score testability 0-10 per the evaluation rubric.
     Challenge designs that score below 5 on testability.
     Propose test strategies for the top approaches in synthesis phase.""")

# Optional: Add security-auditor, llm-integrator based on topic

主要优势： Agent 会实时发挥彼此的创意并唱反调，而不是各自孤立地生成创意。

综合完成后拆解团队：

# After Phase 5 synthesis and design presentation
SendMessage(type="shutdown_request", recipient="system-designer", content="Brainstorm complete")
SendMessage(type="shutdown_request", recipient="backend-thinker", content="Brainstorm complete")
SendMessage(type="shutdown_request", recipient="frontend-thinker", content="Brainstorm complete")
SendMessage(type="shutdown_request", recipient="testability-assessor", content="Brainstorm complete")
# ... shutdown any additional domain teammates
TeamDelete()

备用方案： 如果团队组建失败，请加载 Read("${CLAUDE_PLUGIN_ROOT}/skills/brainstorming/references/phase-workflow.md") 并使用标准的第 2 阶段任务启动方式。

手动清理： 如果 TeamDelete() 未能终止所有 Agent，请按两次 Ctrl+F，强制结束剩余的后台 Agent。

---

核心原则

原则	应用方式
动态选择 Agent	根据主题关键词选择 Agent
并行研究	在一条消息中启动 3-5 个 Agent
记忆优先	研究前先检查图谱中的过往决策
先发散	筛选前先生成 10 个以上的创意
任务跟踪	使用 TaskCreate/TaskUpdate，让进度清晰可见
严格遵循 YAGNI	移除不必要的复杂性

---

相关技能

• ork:architecture-decision-record - 记录头脑风暴期间做出的关键决策
• ork:implement - 头脑风暴完成后执行实现计划
• ork:explore - 深入探索代码库，了解现有模式
• ork:assess - 按维度细分对质量进行 0-10 分评级

参考资料

按需使用 Read("${CLAUDE_PLUGIN_ROOT}/skills/brainstorming/references/<file>") 加载：

文件	内容
phase-workflow.md	详细的 7 阶段说明
divergent-techniques.md	SCAMPER、思维导图等
evaluation-rubric.md	0-10 分评分标准
devils-advocate-prompts.md	挑战模板
socratic-questions.md	需求探索
common-pitfalls.md	需要避免的错误
example-session-dashboard.md	完整示例

---

版本： 4.3.0（2026 年 2 月）- 在评估中增加可测试性评分，并在综合输出中增加测试策略