brainstorm

## Auto Mode When `--yes` or `-y`: Auto-select auto mode, auto-select recommended roles, skip all clarification questions, use defaults. **This skill is brainstorming-only — it produces analysis and feature specs but NEVER executes code or modifies source files.** # Brainstorm ## Usage ```bash $brainstorm "Build real-time collaboration platform" --count 3 $brainstorm -y "Design payment system" --count 5 $brainstorm "Build notification system" --style-skill material-design $brainstorm system-architect --session WFS-xxx $brainstorm ux-expert --include-questions ``` **Flags**: - `-y, --yes`: Skip all confirmations (auto mode) - `--count N`: Number of roles to select (default: 3, max: 9) - `--session ID`: Use existing session - `--skip-questions / --include-questions`: Control interactive Q&A per role - `--style-skill PKG`: Style skill package for ui-designer - `--update`: Update existing role analysis --- ## Overview Dual-mode brainstorming with CSV-driven parallel role analysis. Auto mode runs a full pipeline; single role mode runs one role analysis independently. ``` ┌──────────────────────────────────────────────────────────────────┐ │ BRAINSTORM PIPELINE │ ├──────────────────────────────────────────────────────────────────┤ │ │ │ Phase 1: Mode Detection & Routing │ │ ├─ Parse flags and arguments │ │ └─ Route to Auto Mode or Single Role Mode │ │ │ │ ═══ Auto Mode ═══ │ │ │ │ Phase 2: Interactive Framework Generation │ │ ├─ Context collection → Topic analysis → Role selection │ │ ├─ Generate guidance-specification.md │ │ ├─ Generate roles.csv (1 row per selected role) │ │ └─ User validates (skip if -y) │ │ │ │ Phase 3: Wave Role Analysis (spawn_agents_on_csv) │ │ ├─ spawn_agents_on_csv(role instruction template) │ │ ├─ Each role agent produces analysis.md + sub-documents │ │ └─ discoveries.ndjson shared across role agents │ │ │ │ Phase 4: Synthesis Integration │ │ ├─ Read all role analyses (read-only) │ │ ├─ Cross-role analysis → conflict detection │ │ ├─ Feature spec generation │ │ └─ Output: feature-specs/ + feature-index.json │ │ │ │ ═══ Single Role Mode ═══ │ │ │ │ Phase 3S: Single Role Analysis (spawn_agent) │ │ ├─ spawn_agent(conceptual_planning_agent) │ │ └─ Output: {role}/analysis*.md │ │ │ └──────────────────────────────────────────────────────────────────┘ ``` --- ## Context Flow ``` roles.csv feature-specs/ ┌──────────────┐ ┌──────────────────┐ │ R1: sys-arch │──findings───→│ F-001-auth.md │ │ analysis.md │ │ (cross-role spec) │ ├──────────────┤ ├──────────────────┤ │ R2: ui-design│──findings───→│ F-002-ui.md │ │ analysis.md │ │ (cross-role spec) │ ├──────────────┤ ├──────────────────┤ │ R3: test-str │──findings───→│ F-003-test.md │ │ analysis.md │ │ (cross-role spec) │ └──────────────┘ └──────────────────┘ Two context channels: 1. Directed: role findings → synthesis → feature specs 2. Broadcast: discoveries.ndjson (append-only shared board) ``` --- ## CSV Schema ### roles.csv ```csv id,role,title,focus,deps,wave,status,findings,output_files,error "R1","system-architect","系统架构师","Technical architecture, scalability","","1","pending","","","" "R2","ui-designer","UI设计师","Visual design, mockups","","1","pending","","","" "R3","test-strategist","测试策略师","Test strategy, quality","","1","pending","","","" ``` **Columns**: | Column | Phase | Description | |--------|-------|-------------| | `id` | Input | Role ID: R1, R2, ... | | `role` | Input | Role identifier (e.g., system-architect) | | `title` | Input | Role display title | | `focus` | Input | Role focus areas and keywords | | `deps` | Input | Dependency IDs (usually empty — all wave 1) | | `wave` | Computed | Wave number (usually 1 for all roles) | | `status` | Output | `pending` → `completed` / `failed` | | `findings` | Output | Key discoveries (max 800 chars) | | `output_files` | Output | Generated analysis files (semicolon-separated) | | `error` | Output | Error message if failed | --- ## Available Roles | Role ID | Title | Focus Area | |---------|-------|------------| | `data-architect` | 数据架构师 | Data models, storage strategies, data flow | | `product-manager` | 产品经理 | Product strategy, roadmap, prioritization | | `product-owner` | 产品负责人 | Backlog management, user stories, acceptance criteria | | `scrum-master` | 敏捷教练 | Process facilitation, impediment removal | | `subject-matter-expert` | 领域专家 | Domain knowledge, business rules, compliance | | `system-architect` | 系统架构师 | Technical architecture, scalability, integration | | `test-strategist` | 测试策略师 | Test strategy, quality assurance | | `ui-designer` | UI设计师 | Visual design, mockups, design systems | | `ux-expert` | UX专家 | User research, information architecture, journey | --- ## Session Structure ``` .workflow/active/WFS-{topic}/ ├── workflow-session.json # Session metadata ├── .process/ │ └── context-package.json # Phase 0 context ├── roles.csv # Role analysis state (Phase 2-3) ├── discoveries.ndjson # Shared discovery board └── .brainstorming/ ├── guidance-specification.md # Framework (Phase 2) ├── feature-index.json # Feature index (Phase 4) ├── synthesis-changelog.md # Synthesis audit trail (Phase 4) ├── feature-specs/ # Feature specs (Phase 4) │ ├── F-001-{slug}.md │ └── F-00N-{slug}.md └── {role}/ # Role analyses (Phase 3, immutable) ├── {role}-context.md # Interactive Q&A ├── analysis.md # Main/index document ├── analysis-cross-cutting.md # Cross-feature └── analysis-F-{id}-{slug}.md # Per-feature ``` --- ## Implementation ### Session Initialization ```javascript const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString() // Parse flags const AUTO_YES = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y') const countMatch = $ARGUMENTS.match(/--count\s+(\d+)/) const roleCount = countMatch ? Math.min(parseInt(countMatch[1]), 9) : 3 const sessionMatch = $ARGUMENTS.match(/--session\s+(\S+)/) const existingSessionId = sessionMatch ? sessionMatch[1] : null const skipQuestions = $ARGUMENTS.includes('--skip-questions') const includeQuestions = $ARGUMENTS.includes('--include-questions') const styleSkillMatch = $ARGUMENTS.match(/--style-skill\s+(\S+)/) const styleSkill = styleSkillMatch ? styleSkillMatch[1] : null const updateMode = $ARGUMENTS.includes('--update') // Role detection const VALID_ROLES = [ 'data-architect', 'product-manager', 'product-owner', 'scrum-master', 'subject-matter-expert', 'system-architect', 'test-strategist', 'ui-designer', 'ux-expert' ] const cleanArgs = $ARGUMENTS .replace(/--yes|-y|--count\s+\d+|--session\s+\S+|--skip-questions|--include-questions|--style-skill\s+\S+|--update/g, '') .trim() const firstArg = cleanArgs.split(/\s+/)[0] const isRole = VALID_ROLES.includes(firstArg) // Mode detection let executionMode if (AUTO_YES) { executionMode = 'auto' } else if (isRole) { executionMode = 'single-role' } else if (cleanArgs) { executionMode = 'auto' } else { executionMode = null // Ask user } const topic = isRole ? cleanArgs.replace(firstArg, '').trim() : cleanArgs.replace(/^["']|["']$/g, '') ``` --- ### Phase 1: Mode Detection & Routing **Objective**: Parse arguments, determine execution mode, prepare session. **Steps**: 1. **Detect Mode** ```javascript if (executionMode === null) { const modeAnswer = functions.request_user_input({ questions: [{ question: "Choose brainstorming mode:", header: "Mode", options: [ { label: "Auto Mode (Recommended)", description: "Full pipeline: framework → parallel roles → synthesis" }, { label: "Single Role", description: "Run one role analysis independently" } ] }] }) executionMode = modeAnswer.Mode.startsWith('Auto') ? 'auto' : 'single-role' } ``` 2. **Session Setup** ```javascript let sessionId, sessionFolder if (existingSessionId) { sessionId = existingSessionId sessionFolder = `.workflow/active/${sessionId}` } else if (executionMode === 'auto') { const slug = topic.toLowerCase().replace(/[^a-z0-9\u4e00-\u9fa5]+/g, '-').substring(0, 40) sessionId = `WFS-${slug}` sessionFolder = `.workflow/active/${sessionId}` Bash(`mkdir -p "${sessionFolder}/.brainstorming" "${sessionFolder}/.process"`) // Initialize workflow-session.json Write(`${sessionFolder}/workflow-session.json`, JSON.stringify({ session_id: sessionId, topic: topic, status: 'brainstorming', execution_mode: executionMode, created_at: getUtc8ISOString() }, null, 2)) } else { // Single role mode requires existing session const existing = Bash(`ls -d .workflow/active/WFS-* 2>/dev/null | head -1`).trim() if (!existing) { console.log('ERROR: No active session found. Run auto mode first to create a session.') return } sessionId = existing.split('/').pop() sessionFolder = existing } ``` **Route**: - `executionMode === 'auto'` → Phase 2 - `executionMode === 'single-role'` → Phase 3S --- ### Phase 2: Interactive Framework Generation (Auto Mode) **Objective**: Analyze topic, select roles, generate guidance-specification.md and roles.csv. **Steps**: 1. **Analyze Topic & Select Roles** ```javascript Bash({ command: `ccw cli -p "PURPOSE: Analyze brainstorming topic and recommend ${roleCount} expert roles for multi-perspective analysis. Success = well-matched roles with clear focus areas. TASK: • Analyze topic domain, complexity, and key dimensions • Select ${roleCount} roles from: data-architect, product-manager, product-owner, scrum-master, subject-matter-expert, system-architect, test-strategist, ui-designer, ux-expert • For each role: define focus area, key questions, and analysis scope • Identify potential cross-role conflicts or synergies • Generate feature decomposition if topic has distinct components MODE: analysis CONTEXT: @**/* EXPECTED: JSON: {analysis: {domain, complexity, dimensions[]}, roles: [{id, role, title, focus, key_questions[]}], features: [{id, title, description}]} CONSTRAINTS: Select exactly ${roleCount} roles | Each role must have distinct perspective | Roles must cover topic comprehensively TOPIC: ${topic}" --tool gemini --mode analysis --rule planning-breakdown-task-steps`, run_in_background: true }) // Wait for CLI completion → { analysis, roles[], features[] } ``` 2. **User Validation** (skip if AUTO_YES) ```javascript if (!AUTO_YES) { console.log(`\n## Brainstorm Framework\n`) console.log(`Topic: ${topic}`) console.log(`Domain: ${analysis.domain} | Complexity: ${analysis.complexity}`) console.log(`\nSelected Roles (${roles.length}):`) roles.forEach(r => console.log(` - [${r.id}] ${r.title}: ${r.focus}`)) if (features.length > 0) { console.log(`\nFeatures (${features.length}):`) features.forEach(f => console.log(` - [${f.id}] ${f.title}`)) } const answer = functions.request_user_input({ questions: [{ question: "Approve brainstorm framework?", header: "Validate", options: [ { label: "Approve", description: "Proceed with role analysis" }, { label: "Modify Roles", description: "Change role selection" }, { label: "Cancel", description: "Abort" } ] }] }) if (answer.Validate === "Cancel") return