pm-feature-viabilitylisted

# PM - Feature Viability Assessment ## 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 - after drafting, require the user's review before finalizing; do not close decisions autonomously. --- ## What this skill does A lightweight decision check before committing to build a new feature. Answers three questions before any spec work begins: 1. **Is this worth building now?** (KANO classification - is this Must-be, Performance, Delighter, or Indifferent relative to current product state?) 2. **What is the smallest version that delivers real value?** (MDP - Minimum Desirable Product) 3. **How will we know it worked?** (Success metrics, defined before build) This skill is **not a gate**. If the decision is already made - feature is in the validated roadmap, committed to a customer, or comes from a hard constraint - skip it explicitly and go directly to pm-feature-design. --- ## When to run **Run when:** - New feature initiated internally (idea from team or product, not from validated roadmap) - Unclear whether to build now vs. defer vs. not build