| name | prd-interview |
| description | This skill should be used when conducting PRD interviews, creating product requirements documents, planning new features, documenting bug fixes, or when using commands like "/prd-builder:prd", "/prd-builder:feature", "/prd-builder:bugfix", or "/prd-builder:refine". Provides comprehensive interview frameworks and question templates for building thorough PRDs. |
PRD Interview Skill
Transforms a rough idea into a PRD through a compiled pipeline: fixed question cards
in, an on-disk answer log out, the document assembled one template section per turn,
then a countable gap checklist and contradiction votes. No step holds the whole PRD in
one window; no step relies on conversation memory.
The pipeline (each stage is a phase file in references/)
| Stage | Phase file | What it does |
|---|
| intake | phase-1-intake.md | slug, run creation, the category-subset lookup |
| interview | phase-2-interview.md | one category per step; cards verbatim; answers logged every round |
| assembly | phase-3-section.md | ONE template slot card per turn, fed ONLY its own answer rows |
| gap check | phase-4-gap-check.md | countable checklist; failing rows loop back to their category card |
| coherence | phase-5-coherence.md | subtraction votes per feature + contradiction votes per section pair; saves the PRD |
| handoff | phase-6-handoff.md | architecture recommendation by flag lookup; taskmanager offer |
The four commands are routers over these phases. references/phase-index.md holds the
run-state shape, the per-command step tables, the escalation rows, and the report card.
Interview categories
A brief Launch Framing round (thesis + hero flow) comes first, then the 8 categories:
| Category | Focus Areas | When to Use |
|---|
| Problem & Context | Pain points, current state, why now | Always |
| Users & Customers | Personas, segments, user journeys | Always |
| Solution & Features | Feature list, MVP scope, priorities | Always |
| Technical Implementation | Architecture, stack (default profile), integrations, dependency vetting | Always |
| Business & Value | ROI, pricing, revenue model | Products, monetized features |
| UX & Design | Flows, wireframes, accessibility | UI-facing work |
| Risks & Concerns | Dependencies, assumptions, blockers | Always |
| Testing & Quality | Test strategies, acceptance criteria | Always |
The "When to Use" column is executed as a LOOKUP, never an inference: the subset table
in phase-1-intake.md keys on prdType, an existing-PRD Glob hit, and three stated
flags (internal_tool, monetized, ui_facing). Per-category depth (which card
blocks, how many rounds) is the depth table in phase-2-interview.md.
Question rounds (mechanics)
- Ask 2–4 questions per AskUserQuestion call, maximum 4.
- Questions, headers, options and multiSelect flags come from the card VERBATIM —
references/questions/index.md names exactly one card file per category.
- Provide concrete options; enable multiSelect for non-mutually-exclusive choices;
the tool adds "Other" itself; keep headers under 12 characters.
- Free text only where the card marks "Free text".
- Prefix every call with progress: "Category of : ".
- After a category's last round: a ≤5-bullet summary, then move on.
- Every round appends rows to
answers/<category>.md BEFORE the run file updates —
a killed session resumes mid-interview from disk, never from memory.
Launch discipline (baked into the cards and the template — not re-decided per run)
- Thesis & hero flow first. The PRD opens with a one-line product thesis and the
single hero flow that proves the value; technology comes after, in service of it.
- Lean v1. The launch scope holds only what serves the hero flow; everything else
goes to the sequenced deferred roadmap, each row with the reason it was held back.
- Decide over defer. Ambiguity becomes a Decisions row with a named owner; the
open-questions table holds only what the escalation rows could not resolve.
- No recorded "needed now" justification → the heavy piece is deferred, not built.
- Vet every dependency. Third-party packages must be open source + actively
maintained (verify by search), recorded in the dependency table; first-party/native
preferred.
Default stack
No stack stated → present the profile in references/default-stack.md as the
pre-selected "(Recommended default)" option; the user opts OUT, never in. That file is
the single source for versions and conventions — do not restate them. /feature runs
default to the host product's current stack, falling back to the profile only when the
host stack is unknown or the product is greenfield. Whatever is chosen lands as an
answers/decisions.md row (owner: the user) and surfaces in the PRD Decisions table.
Run-state and resume
State lives at .taskmanager/prd/run.json + .taskmanager/prd/<slug>/ (answers/,
sections/, votes/, gap-report.md). Resume = execute the lowest-seq step not
done/skipped; prior conversation is never an input. Full shape, step tables, and
escalation rows: references/phase-index.md.
Files (load ONE at a time, on the step that names it)
| File | Load when |
|---|
| references/phase-index.md | creating a run / routing a step |
| references/phase-<1..6>-*.md | executing that step |
| references/questions/index.md → ONE card | an interview step |
| references/template-sections/index.md → ONE card | a section step |
| references/design-review.md | the spec of what phases 4–5 replace and enforce |
| references/default-stack.md | the Stack question, or slot 08 with the default profile |
