pm-discovery-reportlisted

# PM - Discovery Report (client-facing) ## Agent mode (`--agent`) Supports `--agent`: runs autonomously in a subagent, drafts the artifact from existing inputs, and returns a short summary + coverage note. - **No flag** → interactive (default); if inputs are heavy, offer agent mode. - **`--agent`** → obey. First check inputs are complete. Anything missing: do NOT invent it - mark `[ASSUMED - what/why]` in the output and summary. Never hallucinate to fill a gap. --- ## What this skill does Produces the document you put in front of the client: what we heard from you, what we learned about your users and processes, where the value is, what we recommend, what's still open. Its job is dual: 1. **Confirmation loop** - "did we understand you correctly?" Errors caught here cost a conversation; errors caught in build cost a sprint. 2. **Credibility** - a structured, insightful read-back of their own business is the strongest expertise signal you can send during discovery. **Two documents, one truth:** `pm-problem-validation` remains the internal convergence artifact (verdict, track completeness, Go/No-Go framing). This report retells the same findings for the client - narrative, no internal scaffolding. Never let the two diverge on facts; they differ only in audience and tone. **Incremental by design:** run it after the first session and re-run after each one. The report header states its own maturity ("Discovery in progress - based on N sessions" → "Final"). An interim repo