brainstorming

applies_to	all-agents
name	brainstorming
description	You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
triggers	["brainstorm","explore","requirements","ideation","creative"]

Brainstorming Ideas Into Designs

Help turn ideas into fully formed designs and specs through natural collaborative dialogue.

Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.

Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity.

Anti-Pattern: "This Is Too Simple To Need A Design"

Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.

Checklist

You MUST create a task for each of these items and complete them in order:

1. Explore project context — check files, docs, recent commits
2. Offer visual companion (if topic will involve visual questions) — this is its own message, not combined with a clarifying question. See the Visual Companion section below.
3. Ask clarifying questions — one at a time, understand purpose/constraints/success criteria. Use Expert Advisor Triage (see below) to only ask the user questions they can uniquely answer.
4. Consult expert advisors — dispatch Design Lead and/or Product CTO subagents to answer technical/UI questions internally. See Expert Advisor Panel section below.
5. Propose 2-3 approaches — with trade-offs and your recommendation, informed by expert advisor input
6. Present design — in sections scaled to their complexity, get user approval after each section
7. Write design doc — save to docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md and commit
8. Spec review loop — dispatch spec-document-reviewer subagent with precisely crafted review context (never your session history); fix issues and re-dispatch until approved (max 3 iterations, then surface to human)
9. User reviews written spec — ask user to review the spec file before proceeding
10. Transition to implementation — invoke writing-plans skill to create implementation plan

Process Flow

digraph brainstorming {
    "Explore project context" [shape=box];
    "Visual questions ahead?" [shape=diamond];
    "Offer Visual Companion\n(own message, no other content)" [shape=box];
    "Ask user ONLY\nproduct/vision questions" [shape=box];
    "Consult Expert Advisors\n(Design Lead + Product CTO)" [shape=box, style=filled, fillcolor=lightyellow];
    "Propose 2-3 approaches" [shape=box];
    "Present design sections" [shape=box];
    "User approves design?" [shape=diamond];
    "Write design doc" [shape=box];
    "Spec review loop" [shape=box];
    "Spec review passed?" [shape=diamond];
    "User reviews spec?" [shape=diamond];
    "Invoke writing-plans skill" [shape=doublecircle];

    "Explore project context" -> "Visual questions ahead?";
    "Visual questions ahead?" -> "Offer Visual Companion\n(own message, no other content)" [label="yes"];
    "Visual questions ahead?" -> "Ask user ONLY\nproduct/vision questions" [label="no"];
    "Offer Visual Companion\n(own message, no other content)" -> "Ask user ONLY\nproduct/vision questions";
    "Ask user ONLY\nproduct/vision questions" -> "Consult Expert Advisors\n(Design Lead + Product CTO)";
    "Consult Expert Advisors\n(Design Lead + Product CTO)" -> "Propose 2-3 approaches";
    "Propose 2-3 approaches" -> "Present design sections";
    "Present design sections" -> "User approves design?";
    "User approves design?" -> "Present design sections" [label="no, revise"];
    "User approves design?" -> "Write design doc" [label="yes"];
    "Write design doc" -> "Spec review loop";
    "Spec review loop" -> "Spec review passed?";
    "Spec review passed?" -> "Spec review loop" [label="issues found,\nfix and re-dispatch"];
    "Spec review passed?" -> "User reviews spec?" [label="approved"];
    "User reviews spec?" -> "Write design doc" [label="changes requested"];
    "User reviews spec?" -> "Invoke writing-plans skill" [label="approved"];
}

The terminal state is invoking writing-plans. Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans.

Expert Advisor Panel

The brainstorming process has access to two expert advisors that answer technical and design questions internally — so the user is only asked questions they can uniquely answer (product vision, business context, user needs).

The Advisors

Advisor	Skill	Answers questions about
Frontend Design	skills/frontend-design.md	Layout, typography, color, spacing, components, responsive strategy, accessibility, interaction patterns, UI architecture
Product CTO	skills/product-cto.md	System architecture, API design, data flow, caching, performance, resilience, observability, security, deployment, testing strategy

Question Triage

Before asking ANY question during brainstorming, classify it:

digraph triage {
    "Question arises" [shape=box];
    "Only user can answer?" [shape=diamond];
    "Ask user" [shape=box, style=filled, fillcolor=lightblue];
    "Design/UI/UX question?" [shape=diamond];
    "Dispatch Frontend Design\nsubagent" [shape=box, style=filled, fillcolor=lightyellow];
    "Architecture/tech question?" [shape=diamond];
    "Dispatch Product CTO\nsubagent" [shape=box, style=filled, fillcolor=lightyellow];
    "Answer yourself\n(general knowledge)" [shape=box];

    "Question arises" -> "Only user can answer?";
    "Only user can answer?" -> "Ask user" [label="yes"];
    "Only user can answer?" -> "Design/UI/UX question?" [label="no"];
    "Design/UI/UX question?" -> "Dispatch Frontend Design\nsubagent" [label="yes"];
    "Design/UI/UX question?" -> "Architecture/tech question?";
    "Architecture/tech question?" -> "Dispatch Product CTO\nsubagent" [label="yes"];
    "Architecture/tech question?" -> "Answer yourself\n(general knowledge)" [label="no"];
}

Ask the user — questions about product intent, business context, target users, scope, priorities:

• "What should this feature do?"
• "Who is the primary user?"
• "What's more important: speed-to-market or completeness?"
• "Which data matters most to your customers?"
• "What's the budget/timeline constraint?"

Consult Frontend Design — questions about how things should look, feel, and flow:

• "Should this be a table or card grid?"
• "What layout pattern works for this dashboard?"
• "How should the navigation hierarchy work?"
• "What states does this component need?"
• "How should this behave on mobile?"

Consult Product CTO — questions about how things should be built:

• "Real-time or polling for this data?"
• "Where should this logic live — edge, server, or client?"
• "What caching strategy fits here?"
• "How should we handle failures from this external API?"
• "What observability do we need?"

How to Dispatch Expert Advisors

After collecting enough product context from the user (usually 2-4 questions), dispatch the advisors as subagents. Dispatch both in parallel when both are relevant.

Subagent prompt template:

You are the [Frontend Design / Product CTO] advisor for a brainstorming session.

Read the skill file at `skills/[frontend-design / product-cto].md` and apply it to the following context.

## Feature Context
[Paste: what the user wants to build, who it's for, key constraints, any decisions already made]

## Project Context
[Paste: relevant tech stack, existing patterns, current architecture from project exploration]

## Questions to Answer
[List the specific technical/design questions that arose during brainstorming]

Provide your analysis using the output format specified in the skill. Be specific and actionable — your recommendations will be incorporated directly into the design spec.

After receiving advisor responses:

• Synthesize their recommendations into your approach proposals (Step 5)
• Present the design with advisor decisions already baked in
• If advisors disagree on an approach, present both options with trade-offs to the user
• Credit the reasoning: "From an architecture perspective, X makes sense because..." / "The UI works better as Y because..."

When NOT to Use Advisors

• Trivial features (copy change, config tweak, simple bugfix) — don't dispatch advisors for work that doesn't involve design or architecture decisions
• User explicitly wants to decide — if the user says "I want a table, not cards", respect that. Advisors inform defaults, they don't override explicit user preferences
• Pure backend logic with no UI and no architecture decisions — just build it

The Process

Understanding the idea:

• Check out the current project state first (files, docs, recent commits)
• Before asking detailed questions, assess scope: if the request describes multiple independent subsystems (e.g., "build a platform with chat, file storage, billing, and analytics"), flag this immediately. Don't spend questions refining details of a project that needs to be decomposed first.
• If the project is too large for a single spec, help the user decompose into sub-projects: what are the independent pieces, how do they relate, what order should they be built? Then brainstorm the first sub-project through the normal design flow. Each sub-project gets its own spec → plan → implementation cycle.
• For appropriately-scoped projects, ask questions one at a time to refine the idea
• Prefer multiple choice questions when possible, but open-ended is fine too
• Only one question per message - if a topic needs more exploration, break it into multiple questions
• Focus on product questions only: purpose, target users, constraints, success criteria. Do NOT ask the user about layout patterns, architecture choices, caching strategies, or component design — those are for the expert advisors.

Exploring approaches:

• Propose 2-3 different approaches with trade-offs
• Present options conversationally with your recommendation and reasoning
• Lead with your recommended option and explain why

Presenting the design:

• Once you believe you understand what you're building, present the design
• Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced
• Ask after each section whether it looks right so far
• Cover: architecture, components, data flow, error handling, testing
• Be ready to go back and clarify if something doesn't make sense

Design for isolation and clarity:

• Break the system into smaller units that each have one clear purpose, communicate through well-defined interfaces, and can be understood and tested independently
• For each unit, you should be able to answer: what does it do, how do you use it, and what does it depend on?
• Can someone understand what a unit does without reading its internals? Can you change the internals without breaking consumers? If not, the boundaries need work.
• Smaller, well-bounded units are also easier for you to work with - you reason better about code you can hold in context at once, and your edits are more reliable when files are focused. When a file grows large, that's often a signal that it's doing too much.

Working in existing codebases:

• Explore the current structure before proposing changes. Follow existing patterns.
• Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.
• Don't propose unrelated refactoring. Stay focused on what serves the current goal.

After the Design

Documentation:

• Write the validated design (spec) to docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md
  • (User preferences for spec location override this default)
• Use elements-of-style:writing-clearly-and-concisely skill if available
• Commit the design document to git

Spec Review Loop: After writing the spec document:

1. Dispatch spec-document-reviewer subagent (see spec-document-reviewer-prompt.md)
2. If Issues Found: fix, re-dispatch, repeat until Approved
3. If loop exceeds 3 iterations, surface to human for guidance

User Review Gate: After the spec review loop passes, ask the user to review the written spec before proceeding:

"Spec written and committed to <path>. Please review it and let me know if you want to make any changes before we start writing out the implementation plan."

Wait for the user's response. If they request changes, make them and re-run the spec review loop. Only proceed once the user approves.

Implementation:

• Invoke the writing-plans skill to create a detailed implementation plan
• Do NOT invoke any other skill. writing-plans is the next step.

Key Principles

• One question at a time - Don't overwhelm with multiple questions
• Multiple choice preferred - Easier to answer than open-ended when possible
• YAGNI ruthlessly - Remove unnecessary features from all designs
• Explore alternatives - Always propose 2-3 approaches before settling
• Incremental validation - Present design, get approval before moving on
• Be flexible - Go back and clarify when something doesn't make sense

Visual Companion

A browser-based companion for showing mockups, diagrams, and visual options during brainstorming. Available as a tool — not a mode. Accepting the companion means it's available for questions that benefit from visual treatment; it does NOT mean every question goes through the browser.

Offering the companion: When you anticipate that upcoming questions will involve visual content (mockups, layouts, diagrams), offer it once for consent:

"Some of what we're working on might be easier to explain if I can show it to you in a web browser. I can put together mockups, diagrams, comparisons, and other visuals as we go. This feature is still new and can be token-intensive. Want to try it? (Requires opening a local URL)"

This offer MUST be its own message. Do not combine it with clarifying questions, context summaries, or any other content. The message should contain ONLY the offer above and nothing else. Wait for the user's response before continuing. If they decline, proceed with text-only brainstorming.

Per-question decision: Even after the user accepts, decide FOR EACH QUESTION whether to use the browser or the terminal. The test: would the user understand this better by seeing it than reading it?

• Use the browser for content that IS visual — mockups, wireframes, layout comparisons, architecture diagrams, side-by-side visual designs
• Use the terminal for content that is text — requirements questions, conceptual choices, tradeoff lists, A/B/C/D text options, scope decisions

A question about a UI topic is not automatically a visual question. "What does personality mean in this context?" is a conceptual question — use the terminal. "Which wizard layout works better?" is a visual question — use the browser.

If they agree to the companion, read the detailed guide before proceeding: skills/brainstorming/visual-companion.md