brainstorming

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. Ask clarifying questions — one at a time, understand purpose/constraints/success criteria. When one option is clearly more idiomatic, decide it yourself instead of asking (see below).
3. Propose 2-3 approaches — with trade-offs and your recommendation
4. Present design — in sections scaled to their complexity, get user approval after each section
5. Write design doc — save to docs/superpowers/YYYY-MM-DD/<topic>/spec.md. Record the choices you made autonomously and why (see below).
6. Spec self-review — quick inline check for placeholders, contradictions, ambiguity, scope (see below)
7. User reviews written spec — ask user to review the spec file before proceeding
8. Transition to implementation — invoke writing-plans skill to create implementation plan

Process Flow

digraph brainstorming {
    "Explore project context" [shape=box];
    "Ask clarifying questions\n(auto-decide idiomatic choices)" [shape=box];
    "Propose 2-3 approaches" [shape=box];
    "Present design sections" [shape=box];
    "User approves design?" [shape=diamond];
    "Write design doc\n(record autonomous choices)" [shape=box];
    "Spec self-review\n(fix inline)" [shape=box];
    "User reviews spec?" [shape=diamond];
    "Invoke writing-plans skill" [shape=doublecircle];

    "Explore project context" -> "Ask clarifying questions\n(auto-decide idiomatic choices)";
    "Ask clarifying questions\n(auto-decide idiomatic choices)" -> "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\n(record autonomous choices)" [label="yes"];
    "Write design doc\n(record autonomous choices)" -> "Spec self-review\n(fix inline)";
    "Spec self-review\n(fix inline)" -> "User reviews spec?";
    "User reviews spec?" -> "Write design doc\n(record autonomous choices)" [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.

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 understanding: purpose, constraints, success criteria

Deciding instead of asking:

• When a choice has several options but one is clearly the more idiomatic, standard, or conventional choice, don't ask — just decide it and move on. Asking the user to rubber-stamp an obvious default wastes their attention.
• Only skip the question when the choice is genuinely clear-cut. If the options represent a real trade-off, a matter of taste, or something that depends on the user's context, ask.
• When judging which option is more idiomatic, the size of the code change is the LOWEST-priority factor. Correctness and correct, clear, understandable code matter far more than keeping the change small. If the more idiomatic option requires a larger change, prefer it anyway — don't pick the inferior option just because it touches less code.
• Every choice you make autonomously MUST be written up in the spec: what the options were, which one you picked, and why. The user reviews the spec later, so this is where they get the chance to override your call. Don't make a silent decision.

Exploring approaches:

• Propose 2-3 different approaches with trade-offs
• Present options conversationally, leading with your recommended option and why
• YAGNI ruthlessly — strip features the goal doesn't need from every approach

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/YYYY-MM-DD/<topic>/spec.md. Use Korean(한국어로 작성하십시오).
  • (User preferences for spec location override this default)
• Include a "Decisions" section that records every choice you made autonomously (rather than asking the user): what the options were, which one you chose, and the reasoning. This is where the user reviews and can override calls you made on their behalf.
• Use elements-of-style:writing-clearly-and-concisely skill if available

Spec Self-Review: After writing the spec document, look at it with fresh eyes:

1. Placeholder scan: Any "TBD", "TODO", incomplete sections, or vague requirements? Fix them.
2. Internal consistency: Do any sections contradict each other? Does the architecture match the feature descriptions?
3. Scope check: Is this focused enough for a single implementation plan, or does it need decomposition?
4. Ambiguity check: Could any requirement be interpreted two different ways? If so, pick one and make it explicit.

Fix any issues inline. No need to re-review — just fix and move on.

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

"Spec written. 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 — the ONLY skill you invoke after brainstorming (see Process Flow above)

Visual Companion

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

Only on explicit request: Do NOT offer or bring up the visual companion on your own. Use it only when the user explicitly asks for it (e.g., "show me mockups", "can you do this in a browser?", "use the visual companion"). Default to text-only brainstorming otherwise. When the user does ask for it, skip straight to reading the detailed guide below and using it.

Per-question decision: Even after the user has asked for it, 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.

Once the user has asked for the companion, read the detailed guide before proceeding: skills/brainstorming/visual-companion.md