pm-scope-brieflisted
Install: claude install-skill ljucask/pureinn-product-development
# PM - Scope Brief
## 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.
- **Review required:** the artifact contains commitments - the IN/OUT/DEFERRED scope cut is decided here for the first time. After drafting, require the user's review before finalizing; never close scope decisions autonomously.
---
## What this skill does
Turns converged discovery into a definition: what exactly gets built. Written for whoever executes - you, your dev team, your employer - and precise enough to run a dev kickoff call from. It is the document a developer reads instead of "make it like company XY".
**When Scope Brief, when PRD:** both fill the same Phase 3b exit slot - pick one.
| Situation | Document |
|---|---|
| Mandate already given: a client commissioned it, an exec directed it, the decision to build is made | **Scope Brief** (this skill). Phase 3a validation and business-model work would re-answer a question that's already answered. |
| Speculative product: you're deciding whether/what to build, market risk is yours | **PRD** via full Phase 3a + 3b (`/pm-prd`). Skipping validation there is skipping your own ri