Brainstorming Ideas Into Designs

Transform rough ideas into fully-formed designs through intelligent agent selection and structured exploration.

Core principle: Analyze the topic, select relevant agents dynamically, explore alternatives in parallel, present design incrementally.

STEP 0: Verify User Intent with AskUserQuestion

BEFORE creating tasks, clarify brainstorming constraints:

python

AskUserQuestion(
  questions=[
    {
      "question": "What type of design exploration?",
      "header": "Type",
      "options": [
        {"label": "Open exploration (Recommended)", "description": "Generate 10+ ideas, evaluate all, synthesize top 3"},
        {"label": "Constrained design", "description": "I have specific requirements to work within"},
        {"label": "Comparison", "description": "Compare 2-3 specific approaches I have in mind"},
        {"label": "Quick ideation", "description": "Generate ideas fast, skip deep evaluation"}
      ],
      "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
    }
  ]
)

Based on answers, adjust workflow:

Open exploration: Full 7-phase process with all agents
Constrained design: Skip divergent phase, focus on feasibility
Comparison: Skip ideation, jump to evaluation phase
Quick ideation: Generate ideas, skip deep evaluation

STEP 0b: Select Orchestration Mode

Choose Agent Teams (mesh — agents debate and challenge ideas) or Task tool (star — all report to lead):

```
ORCHESTKIT_PREFER_TEAMS=1
```
→ Agent Teams mode
Agent Teams unavailable → Task tool mode (default)
Otherwise: Open exploration with 3+ agents → recommend Agent Teams (real-time debate produces better ideas); Quick ideation → Task tool

Aspect	Task Tool	Agent Teams
Idea generation	Each agent generates independently	Agents riff on each other's ideas
Devil's advocate	Lead challenges after all complete	Agents challenge each other in real-time
Cost	~150K tokens	~400K tokens
Best for	Quick ideation, constrained design	Open exploration, deep evaluation

Fallback: If Agent Teams encounters issues, fall back to Task tool for remaining phases.

CRITICAL: Task Management is MANDATORY (CC 2.1.16)

python

# 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")

The Seven-Phase Process

Phase	Activities	Output
0. Topic Analysis	Classify keywords, select 3-5 agents	Agent list
1. Memory + Context	Search graph, check codebase	Prior patterns
2. Divergent Exploration	Generate 10+ ideas WITHOUT filtering	Idea pool
3. Feasibility Fast-Check	30-second viability per idea	Filtered ideas
4. Evaluation & Rating	Rate 0-10, devil's advocate challenge	Ranked ideas
5. Synthesis	Filter to top 2-3, trade-off table	Options
6. Design Presentation	Present in 200-300 word sections	Validated design

See

references/phase-workflow.md

for detailed instructions.

When NOT to Use

Skip brainstorming when:

Requirements are crystal clear and specific
Only one obvious approach exists
User has already designed the solution
Time-sensitive bug fix or urgent issue

Quick Reference: Agent Selection

Topic Example	Agents to Spawn
"brainstorm API for users"	workflow-architect, backend-system-architect, security-auditor
"brainstorm dashboard UI"	workflow-architect, frontend-ui-developer, ux-researcher
"brainstorm RAG pipeline"	workflow-architect, llm-integrator, data-pipeline-engineer
"brainstorm caching strategy"	workflow-architect, backend-system-architect, performance-engineer

Always include:

workflow-architect

for system design perspective.

Agent Teams Alternative: Brainstorming Team

In Agent Teams mode, form a brainstorming team where agents debate ideas in real-time. Dynamically select teammates based on topic analysis (Phase 0):

python

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

# Always include the system design lead
Task(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)
Task(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.""")

Task(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.""")

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

Key advantage: Agents riff on each other's ideas and play devil's advocate in real-time, rather than generating ideas in isolation.

Team teardown after synthesis:

python

# 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")
# ... shutdown any additional domain teammates
TeamDelete()

Fallback: If team formation fails, use standard Phase 2 Task spawns from Phase Workflow.

Key Principles

Principle	Application
Dynamic agent selection	Select agents based on topic keywords
Parallel research	Launch 3-5 agents in ONE message
Memory-first	Check graph for past decisions before research
Divergent-first	Generate 10+ ideas BEFORE filtering
Task tracking	Use TaskCreate/TaskUpdate for progress visibility
YAGNI ruthlessly	Remove unnecessary complexity

Related Skills

```
architecture-decision-record
```
- Document key decisions made during brainstorming
```
implement
```
- Execute the implementation plan after brainstorming completes
```
explore
```
- Deep codebase exploration to understand existing patterns
```
assess
```
- Rate quality 0-10 with dimension breakdown

References

Phase Workflow - Detailed 7-phase instructions
Divergent Techniques - SCAMPER, Mind Mapping, etc.
Evaluation Rubric - 0-10 scoring criteria
Devil's Advocate Prompts - Challenge templates
Socratic Questions - Requirements discovery
Common Pitfalls - Mistakes to avoid
Example Session - Complete example

Version: 4.1.0 (January 2026) - Refactored to progressive loading structure

brainstorming

NPX Install

Tags

SKILL.md Content

Brainstorming Ideas Into Designs

STEP 0: Verify User Intent with AskUserQuestion

STEP 0b: Select Orchestration Mode

CRITICAL: Task Management is MANDATORY (CC 2.1.16)

The Seven-Phase Process

When NOT to Use

Quick Reference: Agent Selection

Agent Teams Alternative: Brainstorming Team

Key Principles

Related Skills

References