|
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071 |
- **Language:** Use `{communication_language}` for all output.
- **Output Language:** Use `{document_output_language}` for documents.
- **Paths:** Bare paths (e.g. `prompts/foo.md`) resolve from the skill root.
-
- # Stage 3: Guided Elicitation
-
- **Goal:** Fill the gaps in what you know. By now you have the user's brain dump, artifact analysis, and web research. This stage is about smart, targeted questioning — not rote section-by-section interrogation.
-
- **Skip this stage entirely in Yolo and Autonomous modes** — go directly to `prompts/draft-and-review.md`.
-
- ## Approach
-
- You are NOT walking through a rigid questionnaire. You're having a conversation that covers the substance of a great product brief. The topics below are your mental checklist, not a script. Adapt to:
- - What you already know (don't re-ask what's been covered)
- - What the user is excited about (follow their energy)
- - What's genuinely unclear (focus questions where they matter)
-
- ## Topics to Cover (flexibly, conversationally)
-
- ### Vision & Problem
- - What core problem does this solve? For whom?
- - How do people solve this today? What's frustrating about current approaches?
- - What would success look like for the people this helps?
- - What's the insight or angle that makes this approach different?
-
- ### Users & Value
- - Who experiences this problem most acutely?
- - Are there different user types with different needs?
- - What's the "aha moment" — when does a user realize this is what they needed?
- - How does this fit into their existing workflow or life?
-
- ### Market & Differentiation
- - What competitive or alternative solutions exist? (Leverage web research findings)
- - What's the unfair advantage or defensible moat?
- - Why is now the right time for this?
-
- ### Success & Scope
- - How will you know this is working? What metrics matter?
- - What's the minimum viable version that creates real value?
- - What's explicitly NOT in scope for the first version?
- - If this is wildly successful, what does it become in 2-3 years?
-
- ## The Flow
-
- For each topic area where you have gaps:
-
- 1. **Lead with what you know** — "Based on your input and my research, it sounds like [X]. Is that right?"
- 2. **Ask the gap question** — targeted, specific, not generic
- 3. **Reflect and confirm** — paraphrase what you heard
- 4. **"Anything else on this, or shall we move on?"** — the soft gate
-
- If the user is giving you detail beyond brief scope (requirements, architecture, platform details, timelines), **capture it silently** for the distillate. Acknowledge it briefly ("Good detail, I'll capture that") but don't derail the conversation.
-
- ## When to Move On
-
- When you have enough substance to draft a compelling 1-2 page executive brief covering:
- - Clear problem and who it affects
- - Proposed solution and what makes it different
- - Target users (at least primary)
- - Some sense of success criteria or business objectives
- - MVP-level scope thinking
-
- You don't need perfection — you need enough to draft well. Missing details can be surfaced during the review stage.
-
- If the user is providing complete, confident answers and you have solid coverage across all four topic areas after fewer than 3-4 exchanges, proactively offer to draft early.
-
- **Transition:** "I think I have a solid picture. Ready for me to draft the brief, or is there anything else you'd like to add?"
-
- ## Stage Complete
-
- This stage is complete when sufficient substance exists to draft a compelling brief and the user confirms readiness. Route to `prompts/draft-and-review.md`.
|