Spark

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.

Scope and Existing Decisions

This process applies to brainstorming and design tasks accepted by this skill. Do not reroute a routine implementation, bug fix, or config edit into brainstorming merely because it involves a design choice. Within a design task, preserve the design approval gate even for a small design.

Reuse answers and approvals already present in the conversation. Explore the codebase before asking for missing facts. Ask only about unresolved decisions that materially affect the design; state reasonable low-risk assumptions and continue. An existing approval applies to the same design and scope, not to newly introduced tradeoffs. Silence is not 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) — request companion consent separately from design approval. See the Visual Companion section below.
3. Resolve missing decisions — reuse context first; ask one material question at a time only when needed
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/spark/YYYY-MM-DD-<topic>-design.md; commit only if already authorized
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. Deliver spec to user and STOP — report the spec file path; do not auto-chain to implementation planning or product implementation

Process Flow

digraph brainstorming {
    "Explore project context" [shape=box];
    "Visual questions ahead?" [shape=diamond];
    "Request Visual Companion consent" [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];
    "Deliver spec path to user and STOP" [shape=doublecircle];

    "Explore project context" -> "Visual questions ahead?";
    "Visual questions ahead?" -> "Request Visual Companion consent" [label="yes"];
    "Visual questions ahead?" -> "Ask clarifying questions" [label="no"];
    "Request Visual Companion consent" -> "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?" -> "Deliver spec path to user and STOP" [label="approved"];
}

The terminal state is delivering the spec to the user. STOP. Do NOT auto-chain to implementation planning or product implementation. Supporting skills for completing the authorized design deliverable are allowed. Report the spec path and end your turn — the user will decide what to do with the spec.

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

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/spark/YYYY-MM-DD-<topic>-design.md
  • (User preferences for spec location override this default)
• Commit the design document only when the user has authorized that commit. Otherwise deliver the file without requiring a commit to finish. Do not infer push or history-rewrite permission from a design request.

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 to <path> and self-reviewed. Please review the document; any requested changes will be incorporated before this design task is marked approved."

Deliver the concrete file path with this review request; report its actual commit status separately. The written-spec approval gate remains in place. If the user requests changes, make them and self-review again. After approval, close the design task; do not start implementation planning unless the user gives a new instruction. An already explicit approval of this exact written version satisfies the gate.

Done — STOP here:

• Report the spec file path to the user and end your turn.
• Do NOT auto-chain to another task; supporting skills remain limited to authorized design work.
• Do NOT start implementation planning or write any code.
• The user will decide what to do with the spec on their own.

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)"

Keep companion consent distinct from design approval. The request may include relevant context; it need not occupy an entire message or end the turn. Use an available asynchronous question mechanism when appropriate. Wait for consent before starting or using the companion, but continue independent text-based analysis while the offer is pending. If they decline or consent remains absent, keep working in text; do not treat silence as consent. Do not repeat an offer already answered in this conversation.

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: visual-companion.md