Brainstorming

Brainstorming Ideas Into Designs

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

Start by classifying how much process the request needs, then work through your path: understand the context, refine the idea, present a design, and get your human partner's approval.

Three Paths

Before your first question, classify the request and say the classification out loud — "this looks bounded, so I'll present a short design here rather than write a spec" — so your human partner can override it:

• Spike — a feasibility question ("can we...", "is it possible...", "quick and dirty is fine") whose output is an answer, not code you keep. Present the question and what you'll try in 2-3 sentences, get a nod, then find out as cheaply as correctness allows. No design doc, no spec file. Report findings as a recommendation; anything you built stays labeled throwaway.
• Bounded — a well-scoped change to code that already exists in this repo: a new flag, a small endpoint, a one-file fix. Understanding the kind of app is not enough — bounded means the flow you are changing is already here to read. If there is no existing flow to change, the task is not bounded. Ask the clarifying questions that matter, present a short design IN CHAT (a few sentences to a few short paragraphs), and STOP. Implementation starts only after your human partner says yes to that design — a bounded task's approval is as hard a gate as an architectural one. No spec file, no implementation plan document.
• Architectural — new projects, new subsystems, changes that restructure how components fit together or alter interfaces others depend on. Follow the full process: questions, approaches, sectioned design, written spec, then the writing-plans skill.

When in doubt between two paths, take the heavier one. The ratchet is one-way: hidden complexity discovered mid-task upgrades the path — stop, say so, and step up. Nothing downgrades mid-task.

Anti-Pattern: "Too Simple To Need Approval"

Every path ends with your human partner approving your intent before implementation. A todo list, a single-function utility, a config change — the design may be two sentences in chat, but you MUST present it and get approval. "Simple" tasks are where unexamined assumptions cause the most wasted work. What scales with simplicity is the artifact, never the approval.

Red Flags

Checklist

Classify first, announce the path, then work the items on that path in order.

On the bounded and architectural paths, you MUST track those items as a task.md artifact (using write_to_file with IsArtifact: true and the task type in ArtifactMetadata). A spike gets no artifact and no visual step — writing a tracking file for a three-sentence probe is exactly the over-ceremony this router exists to remove. Keep the spike in chat.

Spike:

1. Explore project context — enough to frame the probe
2. Present question + probe plan — 2-3 sentences
3. Get approval — a nod is enough
4. Investigate — as cheaply as correctness allows
5. Report findings — a recommendation; label anything built as throwaway

Bounded:

1. Explore project context — use list_dir and grep_search to check files, docs, recent commits
2. Ask clarifying questions — one at a time, the ones that matter
3. Present short design in chat — approach, files touched, testing. Use generate_image if the change is visual and a mockup would be clearer than prose
4. Get approval — STOP and wait for an explicit yes; presenting the design and starting in the same breath is skipping the gate
5. Implement — proceed with the normal development workflow (TDD applies); no plan document

Architectural:

1. Explore project context — use list_dir and grep_search to check files, docs, recent commits. For large codebases, dispatch a TypeName: "research" subagent to explore in parallel while you ask questions.
2. Assess visual needs — note whether upcoming questions have visual aspects. If so, use generate_image for mockups and diagrams as you go. No consent needed — this is a native tool, not a browser session.
3. Ask clarifying questions — one at a time, understand purpose/constraints/success criteria
4. Propose 2-3 approaches — with trade-offs and your recommendation
5. Present design — in sections scaled to their complexity, get user approval after each section
6. Write design doc — save to docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md and commit
7. Spec self-review — quick inline check for placeholders, contradictions, ambiguity, scope (see below)
8. User reviews written spec — ask user to review the spec file before proceeding
9. Transition to implementation — invoke writing-plans skill to create implementation plan

Process Flow

dotCopy code
digraph brainstorming {
    "Classify: spike / bounded / architectural" [shape=diamond];
    "Present question + probe (2-3 sentences)" [shape=box];
    "Ask clarifying questions (bounded)" [shape=box];
    "Present short design in chat" [shape=box];
    "Human approves?" [shape=diamond];
    "Investigate; report recommendation" [shape=doublecircle];
    "Implement via normal workflow (no plan doc)" [shape=doublecircle];
    "Explore project context" [shape=box];
    "Assess visual needs" [shape=box];
    "Ask clarifying questions" [shape=box];
    "Propose 2-3 approaches" [shape=box];
    "Present design sections" [shape=box];
    "User approves design?" [shape=diamond];
    "Write design doc" [shape=box];
    "Spec self-review\n(fix inline)" [shape=box];
    "User reviews spec?" [shape=diamond];
    "Invoke writing-plans skill" [shape=doublecircle];
    "Hidden complexity? Upgrade path" [shape=box];

    "Classify: spike / bounded / architectural" -> "Present question + probe (2-3 sentences)" [label="spike"];
    "Classify: spike / bounded / architectural" -> "Ask clarifying questions (bounded)" [label="bounded"];
    "Classify: spike / bounded / architectural" -> "Explore project context" [label="architectural"];
    "Present question + probe (2-3 sentences)" -> "Human approves?";
    "Ask clarifying questions (bounded)" -> "Present short design in chat";
    "Present short design in chat" -> "Human approves?";
    "Human approves?" -> "Investigate; report recommendation" [label="spike: yes"];
    "Human approves?" -> "Implement via normal workflow (no plan doc)" [label="bounded: yes"];
    "Hidden complexity? Upgrade path" -> "Classify: spike / bounded / architectural";
    "Explore project context" -> "Assess visual needs";
    "Assess visual needs" -> "Ask clarifying questions";
    "Ask clarifying questions" -> "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 self-review\n(fix inline)";
    "Spec self-review\n(fix inline)" -> "User reviews spec?";
    "User reviews spec?" -> "Write design doc" [label="changes requested"];
    "User reviews spec?" -> "Invoke writing-plans skill" [label="approved"];
}

Terminal states are path-bound. Architectural: the ONLY skill you invoke after brainstorming is writing-plans — never frontend-design, mcp-builder, or any other implementation skill. Bounded: after approval, implementation proceeds directly through the normal development workflow; no plan document. Spike: the terminal state is a reported recommendation.

The Process

The subsections below serve the bounded and architectural paths (a spike stops at "present the probe, get a nod"). Sections from Exploring approaches onward are architectural-path depth — for bounded work, context plus a few questions plus a short in-chat design is the whole 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
• When presenting multiple-choice options, use ask_question to render an interactive modal instead of typing numbered options in text
• Focus on understanding: purpose, constraints, success criteria

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
• YAGNI ruthlessly - remove unnecessary features from every approach and design
• When exploring approaches, use search_web to check for existing solutions, libraries, or established patterns before designing from scratch

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 (architectural path)

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 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:

Write the design doc artifact with RequestFeedback: true in the ArtifactMetadata. This prompts the user for structured feedback when their Artifact Review Policy is set to Request Review; if the session doesn't pause for review, ask for approval in chat — the HARD-GATE stands either way.

User feedback may arrive as inline artifact comments — treat each comment as a change request against that section and confirm resolution in the artifact.

If the user requests 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.

Slash Command Recommendations

Suggest these to the user when appropriate:

• /grill-me — when the user wants rapid alignment through an interactive interview instead of the Socratic process
• /goal — when the user wants a long autonomous session ("build X end-to-end, don't stop until done")

Visual Companion

When brainstorming involves visual questions, use native Antigravity tools directly:

Generating mockups:

• Use generate_image with specific, descriptive prompts. Include layout details, color schemes, element placement.
• Bad prompt: "dashboard mockup"
• Good prompt: "Modern project management dashboard with dark theme. Left sidebar with project list and icons. Main area shows a kanban board with 4 columns (Backlog, In Progress, Review, Done). Header bar with search field and notification bell. Clean, minimal design with subtle shadows."

Comparisons:

• Generate 2-3 alternatives when presenting design options
• Embed in an artifact using a carousel for side-by-side review:

  carouselCopy code
  ![Option A: Sidebar layout](/path/to/mockup_a.png)
  <!-- slide -->
  ![Option B: Top-nav layout](/path/to/mockup_b.png)
  

Per-question decision: For each question, decide whether visual or text is better:

• Use generate_image for content that IS visual — mockups, wireframes, layout comparisons, architecture diagrams
• Use text for content that is text — requirements questions, conceptual choices, tradeoff lists, scope decisions

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