메뉴
Use when a manuscript, book concept, opening pages, synopsis, query package, or Book Genesis project needs simulated literary agent, acquiring editor, bookseller, and target-reader review for market viability and publication readiness.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Simula 3 leitores radicalmente distintos avaliando o manuscrito — o Devorador (ritmo), o Crítico (profundidade) e o Hostil (furos). Cada um com instruções profundas para evitar convergência. Reporta onde abandonam, o que confunde, o que encanta. Usar na Fase 4 do book-genesis, antes de submissão, ou quando quiser testar o manuscrito.
Market researcher for the Book Genesis pipeline. Analyzes genre landscape, identifies comp titles, finds market gaps, and gathers data/sources for non-fiction. Never writes narrative prose.
Chaos agent for the Book Genesis pipeline. Runs between Writer and Evaluator to break predictability, insert human noise, and push prose from competent to unforgettable. 8 disruption operations. The agent that introduces wildness into a controlled system.
Dedicated dialogue editing pass — ensures distinct character voices, subtext, natural rhythm, and correct dialogue-to-prose ratio. Runs AFTER prose-craft and BEFORE chaos-engine.
Specializes in chapter openings (hooks) and chapter endings (pulls). Every chapter must start with a reason to keep reading and end with a reason to turn the page. Runs after prose-craft, before chaos-engine. The skill that prevents the reader from putting the book down.
Bash-first mechanical pattern cleanup pipeline — handles em-dash removal, forbidden words, and repetitive structures at scale BEFORE AI agents touch the text. Processes 30+ chapters efficiently.
| name | literary-agent-panel |
| description | Use when a manuscript, book concept, opening pages, synopsis, query package, or Book Genesis project needs simulated literary agent, acquiring editor, bookseller, and target-reader review for market viability and publication readiness. |
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:
Run 4 voices, with separate verdicts:
Read only available materials:
PROJECT_STATE.yamlresearch/market-research.mdfoundation/positioning.mdevaluations/genesis-score.mdIf a required market artifact is missing, flag it as a blocker instead of inventing confidence.
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 verdict. One BLOCK means not market-ready.
Score 1-10 with short evidence:
Write to evaluations/agent-panel.md when inside a project.
# Literary Agent Panel
## Overall Verdict
[PASS/FLAG/BLOCK] - [one sentence why]
## Panel Verdicts
| Role | Verdict | Reason |
|---|---|---|
| Literary Agent | ... | ... |
| Acquiring Editor | ... | ... |
| Bookseller/Buyer | ... | ... |
| Target Reader | ... | ... |
## Scores
| Criterion | Score | Evidence |
|---|---:|---|
| Category clarity | ... | ... |
| Reader promise | ... | ... |
| Opening-page pull | ... | ... |
| Voice distinctiveness | ... | ... |
| Comp-title fit | ... | ... |
| Commercial pacing | ... | ... |
| Emotional stakes | ... | ... |
| Shelf/thumbnail fit | ... | ... |
| Submission package strength | ... | ... |
| Launch/platform leverage | ... | ... |
## Top Rejection Risks
1. ...
2. ...
3. ...
## Fix Before Submission
1. ...
2. ...
3. ...
## Best Market Angle
[Specific positioning angle]
## Query/Package Notes
[What to change in logline, synopsis, comps, cover brief, or author bio]