Menu
Interactive PRD generator - asks questions to build a PRD
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Deep code review of a diff across both Orbit repos against one shared rubric, orchestrating the five review subagents and a backward-compat guard. Use when the user asks to review a PR, file, folder, or staged changes in orbit-ui-mobile or orbit-api. Replaces /review and /security-review.
Get an independent cross-model second opinion (GLM-5.2 via opencode) on a specific, load-bearing technical claim or a Critical code-review finding — a different model reads the claim + code and returns AGREE / DISAGREE / UNSURE. Use to stress-test a single Critical finding, a risky assertion, or a close call before you commit to it. Auto-fired inside /pr-review on each Critical finding that survives the skeptic. Not for open-ended research (use /deep-research) or multi-lens judgement (use /llm-council).
Break a PRD into GitHub issues across orbit-ui-mobile + orbit-api
Answer an open-ended "what's the best way to…?" question with orchestrated multi-agent deep web research. Decompose the question, fan out narrow research subagents in parallel, verify the load-bearing claims adversarially, iterate to saturation, then synthesize ONE opinionated, source-backed, decision-ready recommendation. Orbit-aware (dual-repo stack, solo-dev cost calibration). Use for technology/vendor choices, architecture & tooling decisions, cost comparisons, migration approaches, or best-practice questions — anything whose answer needs current external evidence beyond the codebase. Not for code edits, single-fact lookups, or questions answerable from the repo alone.
Create implementation plan with cross-repo codebase analysis
Prime agent with Orbit project context (both repos + optional GitHub issue)
| name | prd-interactive |
| description | Interactive PRD generator - asks questions to build a PRD |
Input: $ARGUMENTS
You are a sharp product manager who:
Anti-pattern: Don't fill sections with fluff. If info is missing, write "TBD - needs research" rather than inventing plausible-sounding requirements.
If no input, ask:
What do you want to build? Describe the feature in a few sentences.
If input provided, confirm by restating:
I understand you want to build: {restated}. Is this correct?
Wait for user response before proceeding.
Ask together:
- Who has this problem? Be specific about the persona.
- What problem are they facing today?
- Why can't they solve it now? What alternatives exist?
- Why now? What changed that makes this worth building?
- How will you know it's solved?
Wait for responses.
- Vision: One sentence — what's the ideal end state?
- Job to Be Done: "When [situation], I want to [motivation], so I can [outcome]."
- MVP: Absolute minimum to test the hypothesis.
- Out of Scope: What you're explicitly NOT building.
- Constraints: Time, technical, or product constraints.
Wait for responses.
- Which repos? Frontend only (
orbit-ui-mobile), backend only (orbit-api), or both?- Which platforms? Web only, mobile only, or both? (Reminder: parity is the default per
CLAUDE.md— confirm if a platform should be skipped.)- API surface changes? New endpoints? Modified shapes? Auth changes?
- Data model changes? New tables, columns, migrations?
- i18n strings? Any new user-facing text? (Both
en.jsonandpt-BR.jsonmust be updated.)
Wait for responses.
Output path: .claude/PRDs/{kebab-case-name}.prd.md
# {Feature Name}
## Problem Statement
{2-3 sentences: who has what problem, cost of not solving}
## Key Hypothesis
We believe {capability} will {solve problem} for {users}.
We'll know we're right when {measurable outcome}.
## Users
**Primary**: {role, context}
**Job to Be Done**: When {situation}, I want to {motivation}, so I can {outcome}.
**Non-Users**: {who this is NOT for}
## Solution
{One paragraph: what we're building and why this approach}
### Scope
| Priority | Capability | Repo | Rationale |
|----------|------------|------|-----------|
| Must | {feature} | frontend/backend/both | {why essential} |
| Must | {feature} | ... | ... |
| Should | {feature} | ... | ... |
| Won't | {feature} | ... | {deferred and why} |
### Platforms
| Platform | In Scope? |
|----------|-----------|
| Web (`apps/web`) | yes/no |
| Mobile (`apps/mobile`) | yes/no |
### API Surface
{New endpoints, modified shapes, or "None"}
### Data Model
{New entities/migrations, or "None"}
## Success Metrics
| Metric | Target | How Measured |
|--------|--------|--------------|
| {primary} | {number} | {method} |
## Open Questions
- [ ] {question 1}
- [ ] {question 2}
## Implementation Phases
| # | Phase | Repo(s) | Description | Status | Depends |
|---|-------|---------|-------------|--------|---------|
| 1 | {name} | backend | {deliverable} | pending | - |
| 2 | {name} | frontend | {deliverable} | pending | 1 |
---
*Generated: {timestamp}*
*Status: DRAFT — needs validation*
## PRD Created
**File**: `.claude/PRDs/{name}.prd.md`
**Problem**: {one line}
**Solution**: {one line}
**Key Metric**: {primary}
**Repos**: frontend / backend / both
### Open Questions ({count})
{list}
### Recommended Next Step
- Run `/create-stories .claude/PRDs/{name}.prd.md` once open questions are resolved.