pm-personaslisted

# PM - Customer Segments & Personas ## 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 Takes raw VOC (Voice of Customer) data - interview transcripts, synthetic interview outputs, survey results, behavioral observations - and produces: 1. Customer Segments (distinct groups with shared needs) 2. Personas (1-2 per key segment) 3. Early Adopters Profile This is a "bring your data" skill. Claude synthesizes, structures, and formalizes patterns from the input. No invented personas without data. Run this before `jtbd-building` - JTBD analysis uses personas as input. **Provenance discipline:** every persona claim carries its source class - real VOC (interviews, surveys, observation), `[CLIENT-ASSERTED]` (a client/sponsor described their own users - input, not evidence), or `[ASSUMED]` (our inference). In commissioned builds the client's description of their users is the most common input - treat it as a hypothesis to valida