persona-reviewlisted

# /persona-review ## Goal Answer one question with evidence from a **diverse panel of ordinary users**: *how would real people react to this?* You seat five synthetic-but-grounded Korean personas — sampled from Korean census distributions — in front of a target artifact and report their reactions, frictions, and what to change. This is a **citizen/user lens**: comprehension, trust, tone, and clarity. It stands beside `code-reviewer` (correctness) and `security-reviewer` (vulnerabilities) and replaces neither. A panelist may *voice* a worry that is really a security or correctness concern ("is my data safe here?") — capture it as a user worry and route it to the right reviewer; do not adjudicate it here. **Leading word: panel.** Five independent voices, then one synthesis — not one voice pretending to be five. ## Inputs - **Target** — the artifact under review: a URL, a file path, pasted copy, a screenshot description, or a component. Required. - **Question** (optional) — what to probe: first-read comprehension, trust, tone, call-to-action clarity, pricing legibility. Default when unstated: *first-time-visitor comprehension + trust*. - **Catalog** — `skills/persona-review/personas/catalog.json` (shipped). If it is missing or unparseable, stop and say so — do not invent personas. ## Steps ### 1. Load the catalog Read `skills/persona-review/personas/catalog.json` and confirm `personas` is a non-empty list. Each entry carries `age`, `sex`, `province`, `occupation