literary-agent-panel

# Literary Agent Panel This skill stress-tests a book from the market side. It does not write chapters. It decides whether a real agent, editor, bookseller, or target reader would keep reading, ask for pages, buy, recommend, or reject. Use after: - book idea/concept exists - market research exists or is being questioned - first 10 pages need commercial review - full draft needs submission readiness review - editorial package needs agent/editor feedback - Book Genesis reaches audit, final score, or delivery ## Panel Roles Run 4 voices, with separate verdicts: 1. Literary Agent: query hook, category clarity, comp fit, sellability, submission risk. 2. Acquiring Editor: manuscript strength, list fit, editorial labor, positioning. 3. Bookseller/Category Buyer: shelf fit, cover/copy expectations, reader promise. 4. Target Reader: opening pull, emotional promise, readability, recommendability. ## Review Inputs Read only available materials: - `PROJECT_STATE.yaml` - `research/market-research.md` - `foundation/positioning.md` - opening pages or chapter files - synopsis/query/cover copy - `evaluations/genesis-score.md` If a required market artifact is missing, flag it as a blocker instead of inventing confidence. ## Verdict Scale Use one verdict per panel role: - `PASS`: would continue, request, acquire, stock, or recommend. - `FLAG`: viable but needs specific fixes. - `BLOCK`: would reject or abandon for commercial/product reasons. Overall verdict is the weakest role ver...