agentleFS
Sign inStart free
jodyjdcjodyjdc/ultimate-best-seller-studio/skills/literary-agent-panel/SKILL.md

literary-agent-panel

Skill2 starsChanged 5 months agoMITView on GitHub

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.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run 4 voices, with separate verdicts:

    line 21
  2. Distinctive:

    Read only available materials:

    line 30
  3. Distinctive:

    If a required market artifact is missing, flag it as a blocker instead of inventing confidence.

    line 39
  4. Distinctive:

    Use one verdict per panel role:

    line 43
  5. Very specific:

    Write to evaluations/agent-panel.md when inside a project.

    line 68
  6. Distinctive:

    Use current-market logic. If comp titles are old, flag.

    line 118
  7. Distinctive:

    Never promise bestseller status.

    line 119

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 verdict. One BLOCK means not market-ready.

Evaluation Criteria

Score 1-10 with short 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

Output Format

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]

Rules

  • Be candid. Do not flatter weak work.
  • Use current-market logic. If comp titles are old, flag.
  • Never promise bestseller status.
  • Separate taste objections from commercial blockers.
  • For Portuguese projects, evaluate Brazilian/Portuguese-language market fit unless user asks global/US.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free