Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what problem is being solved, present the product direction 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 product direction and the user has approved it. This applies to EVERY project regardless of perceived simplicity.
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 output can be short for truly simple projects, but you MUST present it and get approval.
- If the user asks for market context or competitor understanding first, invoke `market-research` before proposing approaches and treat `docs/research/{date}-{topic}.md` as an upstream input artifact
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, and scope boundaries
4.**Propose 2-3 product approaches** - with trade-offs and your recommendation
5.**Present product direction** - in sections scaled to their complexity, get user approval after each section
6.**Write product direction doc** - save to `docs/brainstorm/{date}-{feature}-design.md`
7.**Spec self-review** - quick inline check for placeholders, contradictions, ambiguity, and scope (see below)
8.**User reviews written spec** - ask user to review the spec file before proceeding
9.**Transition to PRD writing** - invoke `write-a-prd`
**The terminal state is invoking `write-a-prd`.** Do NOT invoke any implementation skill. The ONLY skill you invoke after brainstorming is `write-a-prd`.
- Check out the current project state first (docs, existing product behavior, recent commits) only to understand product context and constraints
- Before asking detailed questions, assess scope: if the request describes multiple independent subsystems, flag this immediately
- If the project is too large for a single spec, help the user decompose into sub-projects, then brainstorm the first sub-project through the normal flow
> "The spec document has been written and submitted to `<path>`. Before we start writing the PRD, please review it and let me know if you need any changes made."
- Invoke `write-a-prd` using `docs/brainstorm/{date}-{feature}-design.md` as the primary input artifact and `docs/research/{date}-{topic}.md` as an optional supporting input artifact
- Do NOT invoke any other skill. `write-a-prd` is the next step.
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 would be easier to explain if shown in a web browser. I can prepare mockups, diagrams, side-by-sides, and other visuals for you anytime. This feature is new and uses more tokens. Want to try it out? (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?**
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.
