| name | brainstorm |
| description | Unified brainstorming skill with dual-mode operation โ auto mode (framework generation, parallel multi-role analysis, cross-role synthesis) and single role analysis. Triggers on "brainstorm", "ๅคด่้ฃๆด". |
| allowed-tools | Skill(*), Agent(conceptual-planning-agent, context-search-agent), AskUserQuestion(*), TodoWrite(*), Read(*), Write(*), Edit(*), Glob(*), Bash(*) |
Brainstorm
Unified brainstorming skill combining interactive framework generation, multi-role parallel analysis, and cross-role synthesis into a single entry point with two operational modes.
Architecture Overview
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ /brainstorm โ
โ Unified Entry Point + Interactive Routing โ
โโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
โโโโโโโโโโโดโโโโโโโโโโ
โ โ
โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโ
โ Auto Mode โ โ Single Role Mode โ
โ (่ชๅจๆจกๅผ) โ โ (ๅ่ง่ฒๅๆๆจกๅผ) โ
โโโโโโโโโโฌโโโโโโโโโ โโโโโโโโโโฌโโโโโโโโโโ
โ โ
โโโโโโโโโโผโโโโโโโโโ โ
โ โ โ โ
Phase 2 Phase 3 Phase 4 Phase 3
Artifacts NรRole Synthesis 1รRole
(7ๆญฅ) Analysis (8ๆญฅ) Analysis
ๅนถ่ก (4ๆญฅ)
Data Flow:
Auto Mode:
Phase 2 (artifacts) โ guidance-specification.md + selected_roles[]
โ Phase 3 (N ร role-analysis) โ {role}/analysis*.md (immutable)
โ Phase 4 (synthesis) โ feature-specs/ + feature-index.json + synthesis-changelog.md
Single Role Mode:
Phase 3 (1 ร role-analysis) โ {role}/analysis*.md
Key Design Principles
- Dual-Mode Routing: Interactive mode selection via AskUserQuestion, with parameter-based auto-detection
- Progressive Phase Loading: Phase files loaded on-demand via
Ref: markers, not all at once
- Task Attachment/Collapse: Sub-tasks attached during phase execution, collapsed after completion
- Session Continuity: All phases share session state via workflow-session.json
- Auto-Continue Execution: Phases chain automatically without user intervention between them
- SPEC.md Quality Alignment: Guidance specification and role analysis follow SPEC.md standards (Concepts & Terminology, Non-Goals, Data Model, State Machine, RFC 2119 constraints)
- Template-Driven Analysis: Role-specific templates (e.g., system-architect) ensure consistent, high-quality outputs
- Quality Gates: Automated validation of guidance specification and role analysis against quality standards
Auto Mode
When --yes or -y: Auto-select auto mode, skip interactive routing question, auto-select recommended roles, skip all clarification questions, use default answers.
Execution Flow
Phase 1: Mode Detection & Interactive Routing
Ref: phases/01-mode-routing.md
Parse arguments, detect mode from flags/parameters, or ask user via AskUserQuestion.
Mode Detection Rules:
- If
--yes or -y flag present โ Auto Mode (no question asked)
- If first arg matches a known role name โ Single Role Mode (no question asked)
- If
--session flag present without role name โ Ask user
- Otherwise โ Ask user via AskUserQuestion
Output: execution_mode ("auto" | "single-role"), parsed parameters
Auto Mode Execution (execution_mode = "auto")
Phase 1.5: Terminology & Boundary Definition
- Extract 5-10 core domain terms from user input and Phase 1 context
- Generate terminology table (term, definition, aliases, category)
- Collect Non-Goals via AskUserQuestion (ๆ็กฎๆ้ค็่ๅด)
- Store to
session.terminology and session.non_goals
Phase 2: Interactive Framework Generation
Ref: phases/02-artifacts.md
Seven-phase interactive workflow: Context collection โ Topic analysis โ Role selection โ Role questions โ Conflict resolution โ Final check โ Generate specification.
Input: topic description, --count N, --yes flag
Output: guidance-specification.md (with Concepts & Terminology, Non-Goals, RFC 2119 constraints), workflow-session.json (selected_roles[], session_id)
TodoWrite: Attach 7 sub-tasks (Phase 0-5), execute sequentially, collapse on completion.
Phase 3: Parallel Role Analysis
Ref: phases/03-role-analysis.md
Execute role analysis for EACH selected role in parallel (excluding ui-designer, which runs sequentially in Phase 3.5).
Input: selected_roles[] from Phase 2, session_id, guidance-specification.md
Output: {role}/analysis*.md for each role
Parallel Execution: Launch N role-analysis calls simultaneously (one message with multiple Skill invokes). Each role with --skip-questions flag. Note: ui-designer is excluded from this parallel batch โ it runs in Phase 3.5 with access to all text-role analyses.
For ui-designer: append --style-skill {package} if provided.
Template-Driven Analysis:
- Load role-specific template if exists (e.g.,
templates/role-templates/system-architect-template.md)
- Inject template into agent prompt as required structure
- For system-architect: MUST include Data Model, State Machine, Error Handling, Observability, Configuration Model, Boundary Scenarios
Quality Validation:
- After analysis generation, invoke
role-analysis-reviewer-agent to validate against template
- Check MUST have sections (blocking), SHOULD have sections (warning), quality checks (RFC keywords, valid diagrams)
- Output validation report with score and recommendations
TodoWrite: Attach N parallel sub-tasks, execute concurrently, collapse on completion.
Phase 3.5: UI Design Exploration
Ref: phases/03a-ui-design-exploration.md
Sequential phase after text-role analyses complete. Generates tangible UI artifacts (HTML prototypes, ASCII mockups, or API sketches) based on project type detection.
Input: all role analyses from Phase 3 (read-only), guidance-specification.md, style_skill (optional)
Output: html-prototypes/ or ascii-mockups/ or api-sketches/ directory with feature-index.json
Skip Conditions: project type is library/service, no ui-designer in selected_roles, --yes mode without --ui-explore
Optional Review: If 2+ prototypes and not --yes, load Ref: ~/.ccw/workflows/brainstorm-visualize.md for multi-round interactive review with intelligent grouping.
TodoWrite: Attach single task with sub-tasks (Detection โ Generate โ Validate โ Review โ Feedback), collapse on completion.
Phase 4: Synthesis Integration
Ref: phases/04-synthesis.md
Six-phase synthesis: Discovery โ File discovery โ Cross-role analysis โ User interaction โ Spec generation (single agent, sequential) + Conditional review โ Finalization. Role analysis files are read-only (never modified). Spec is the final synthesis artifact.
Input: session_id from Phase 2, all role analysis files from Phase 3 (read-only)
Output: feature-specs/, feature-index.json, synthesis-changelog.md
TodoWrite: Attach synthesis sub-tasks, execute sequentially, collapse on completion.
Single Role Mode Execution (execution_mode = "single-role")
Phase 3: Single Role Analysis
Ref: phases/03-role-analysis.md
Execute role analysis for ONE specified role with optional interactive context gathering.
Input: role_name, --session, --update, --include-questions, --skip-questions, --style-skill
Output: {role}/analysis*.md
TodoWrite: Attach 4 sub-tasks (Detection โ Context โ Agent โ Validation), execute sequentially.
Phase Reference Documents (read on-demand when phase executes):
Core Rules
- Start with Mode Detection: First action is Phase 1 (parse args + detect mode)
- Interactive Routing: If mode cannot be determined from args, ASK user via AskUserQuestion
- No Preliminary Analysis: Do not analyze topic before Phase 2 - artifacts handles all analysis
- Parse Every Output: Extract selected_roles from workflow-session.json after Phase 2
- Auto-Continue via TodoList: Check TodoList status to execute next pending phase automatically
- Task Attachment Model: Skill and Task executes attach sub-tasks to current workflow
- โ ๏ธ CRITICAL: DO NOT STOP: Continuous multi-phase workflow in auto mode. After executing all attached tasks, immediately collapse them and execute next phase
- Parallel Execution: Auto mode Phase 3 attaches multiple agent tasks simultaneously for concurrent execution
- Single Role Independence: Single role mode operates independently without requiring artifacts or synthesis
Input Processing
Parameter Parsing
const args = parseArguments(user_input);
const auto_yes = args.includes('--yes') || args.includes('-y');
const count = extractFlag(args, '--count', 3);
const session_id = extractFlag(args, '--session', null);
const update_mode = args.includes('--update');
const include_questions = args.includes('--include-questions');
const skip_questions = args.includes('--skip-questions');
const style_skill = extractFlag(args, '--style-skill', null);
const VALID_ROLES = [
'data-architect', 'product-manager', 'product-owner', 'scrum-master',
'subject-matter-expert', 'system-architect', 'test-strategist',
'ui-designer', 'ux-expert'
];
const first_arg = args[0];
const is_role = VALID_ROLES.includes(first_arg);
if (auto_yes) {
execution_mode = 'auto';
topic = extractTopic(args);
} else if (is_role) {
execution_mode = 'single-role';
role_name = first_arg;
} else {
execution_mode = null;
topic = extractTopic(args);
}
Usage Examples
/brainstorm "Build real-time collaboration platform" --count 3
/brainstorm -y "GOAL: Build platform SCOPE: 100 users" --count 5
/brainstorm "Design payment system" --style-skill material-design
/brainstorm system-architect --session WFS-xxx
/brainstorm ux-expert --include-questions
/brainstorm ui-designer --session WFS-xxx --update --style-skill material-design
/brainstorm product-manager --skip-questions
/brainstorm --session WFS-xxx
/brainstorm
Data Flow
Phase 1 (Mode Routing):
Input: user arguments
Output: execution_mode, parsed_params
โ
โโโโโโโโโดโโโโโโโโ
Auto Single Role
โ โ
Phase 2: Phase 3:
Input: topic, count, auto_yes
Output: session_id โโโโโโโโโโโโโโ Input: role_name, session_id
selected_roles[] skip/include questions
guidance-specification.md style_skill
โ Output: {role}/analysis*.md
Phase 3:
Input: selected_roles[], session_id
guidance-specification.md
style_skill (for ui-designer)
Output: {role}/analysis*.md (N files, immutable after this point)
โ
Phase 3.5:
Input: all analysis*.md (read-only), guidance-specification.md, style_skill
Output: html-prototypes/ OR ascii-mockups/ OR api-sketches/
feature-index.json, review_decisions (optional)
โ
Phase 4:
Input: session_id, all analysis files (read-only)
Output: feature-specs/F-{id}-{slug}.md
feature-index.json
synthesis-changelog.md
TodoWrite Pattern
Auto Mode Lifecycle
Initial โ Phase 1 Mode Routing (completed)
โ Phase 2 Artifacts (in_progress)
โ 7 sub-tasks ATTACHED (Phase 0-5)
โ Execute sequentially
โ Sub-tasks COLLAPSED
โ Phase 3 Parallel Role Analysis (in_progress)
โ N role sub-tasks ATTACHED simultaneously (excluding ui-designer)
โ Execute concurrently
โ Sub-tasks COLLAPSED
โ Phase 3.5 UI Design Exploration (in_progress)
โ Sub-tasks: Detection โ Generate โ Validate โ Review โ Feedback
โ Execute sequentially
โ Sub-tasks COLLAPSED
โ Phase 4 Synthesis (in_progress)
โ 8 sub-tasks ATTACHED
โ Execute sequentially
โ Sub-tasks COLLAPSED
โ All completed
Single Role Mode Lifecycle
Initial โ Phase 1 Mode Routing (completed)
โ Phase 3 Role Analysis (in_progress)
โ 4 sub-tasks ATTACHED (Detection โ Context โ Agent โ Validation)
โ Execute sequentially
โ Sub-tasks COLLAPSED
โ Completed
Initial TodoWrite (Auto Mode)
[
{"content": "Phase 1: Mode detection and parameter parsing", "status": "in_progress", "activeForm": "Detecting mode"},
{"content": "Phase 2: Interactive Framework Generation", "status": "pending", "activeForm": "Generating framework"},
{"content": "Phase 3: Parallel Role Analysis", "status": "pending", "activeForm": "Executing parallel analysis"},
{"content": "Phase 3.5: UI Design Exploration", "status": "pending", "activeForm": "Generating UI prototypes"},
{"content": "Phase 4: Synthesis Integration", "status": "pending", "activeForm": "Executing synthesis"}
]
Initial TodoWrite (Single Role Mode)
[
{"content": "Phase 1: Mode detection and parameter parsing", "status": "in_progress", "activeForm": "Detecting mode"},
{"content": "Phase 3: Single role analysis for {role_name}", "status": "pending", "activeForm": "Executing role analysis"}
]
Session Management
โก FIRST ACTION: Check .workflow/active/ for existing sessions
Multiple Sessions Support:
- Different Claude instances can have different brainstorming sessions
- If multiple sessions found, prompt user to select
- If single session found, use it
- If no session exists:
- Auto mode: Create
WFS-[topic-slug]
- Single role mode: ERROR if no session (must run auto mode first)
Session Continuity: All phases share session state via workflow-session.json
Available Roles
| Role ID | Title | Focus Area |
|---|
data-architect | ๆฐๆฎๆถๆๅธ | Data models, storage strategies, data flow |
product-manager | ไบงๅ็ป็ | Product strategy, roadmap, prioritization |
product-owner | ไบงๅ่ด่ดฃไบบ | Backlog management, user stories, acceptance criteria |
scrum-master | ๆๆทๆ็ป | Process facilitation, impediment removal |
subject-matter-expert | ้ขๅไธๅฎถ | Domain knowledge, business rules, compliance |
system-architect | ็ณป็ปๆถๆๅธ | Technical architecture, scalability, integration |
test-strategist | ๆต่ฏ็ญ็ฅๅธ | Test strategy, quality assurance |
ui-designer | UI่ฎพ่ฎกๅธ | Visual design, mockups, design systems |
ux-expert | UXไธๅฎถ | User research, information architecture, journey |
Role Selection: Auto mode โ handled by artifacts (Phase 2). Single role mode โ user specifies directly.
Output Structure
.workflow/active/WFS-{topic}/
โโโ workflow-session.json # Session metadata ONLY
โโโ .process/
โ โโโ context-package.json # Phase 0 output (auto mode)
โโโ .brainstorming/
โโโ guidance-specification.md # Framework (Phase 2, auto mode)
โโโ feature-index.json # Feature index (Phase 4, auto mode, feature_mode)
โโโ synthesis-changelog.md # Synthesis decisions audit trail (Phase 4, auto mode)
โโโ feature-specs/ # Feature specs (Phase 4, auto mode, feature_mode)
โ โโโ F-001-{slug}.md
โ โโโ F-00N-{slug}.md
โโโ specs/
โ โโโ terminology-template.json # Terminology schema
โโโ templates/
โ โโโ role-templates/
โ โโโ system-architect-template.md # System architect analysis template
โโโ agents/
โ โโโ role-analysis-reviewer-agent.md # Role analysis validation agent
โโโ html-prototypes/ # Phase 3.5 (web/mobile/desktop-gui)
โ โโโ README.md # Prototype summary
โ โโโ feature-index.json # File-to-feature mapping
โ โโโ {feature-slug}.html # Self-contained prototypes
โโโ ascii-mockups/ # Phase 3.5 (cli projects)
โ โโโ {feature-slug}.md
โโโ api-sketches/ # Phase 3.5 (library/service projects)
โ โโโ {feature-slug}.md
โโโ {role}/ # Role analyses (IMMUTABLE after Phase 3)
โ โโโ {role}-context.md # Interactive Q&A responses
โ โโโ analysis.md # Main/index document
โ โโโ analysis-cross-cutting.md # Cross-feature (feature_mode)
โ โโโ analysis-F-{id}-{slug}.md # Per-feature (feature_mode)
โโโ synthesis-specification.md # Integration (Phase 4, non-feature_mode only)
Error Handling
| Error | Recovery | Mode |
|---|
| Invalid role name | Show valid roles list, ask again | Single Role |
| No active session | Auto mode: create new. Single role: error with guidance | Both |
| Role selection failure | Default to product-manager | Auto |
| Agent execution failure | Agent-specific retry with minimal dependencies | Both |
| Template loading issues | Graceful degradation | Both |
| Synthesis conflicts | Highlight disagreements without forced resolution | Auto |
| Context overflow (>100KB) | Read only analysis.md index files | Auto |
Context Overflow Protection:
- Per-role limits: < 3000 words main, < 2000 words sub-docs, max 5 sub-docs
- Synthesis protection: If total > 100KB, read only
analysis.md (not sub-documents)
- Recovery: reduce scope (--count 2) โ use --summary-only โ manual synthesis
Coordinator Checklist
Pre-Phase Actions:
Post-Phase Actions:
Related Commands
Prerequisites:
/workflow:session:start - Start a new workflow session (optional, brainstorm creates its own)
Follow-ups (after brainstorm completes):
/workflow-plan --session {sessionId} - Generate implementation plan
/workflow:brainstorm:synthesis --session {sessionId} - Run synthesis standalone (if skipped)
Reference Information
Template Source: ~/.ccw/workflows/cli-templates/planning-roles/
Style SKILL Packages: .claude/skills/style-{package-name}/