book-bestseller-studio
Skill2 starsChanged 5 months agoMITView on GitHub
Use when the user wants a complete book-production system aimed at commercial viability, bestseller positioning, agent/editor readiness, or launch readiness. Orchestrates book-genesis, book-researcher, literary-agent-panel, book-editor, copy-editing, humanizer-pro, editorial-package, launch-strategy, and content-strategy.
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- beta-readerSkill
- book-editorSkill
- book-genesis-coreSkill
- book-genesis-fullSkill
- book-genesisSkill
- book-researcherSkill
- book-swarm-panelSkill
- copy-editingSkill
- chaos-engineSkill
- dialogue-polishSkill
- hook-craftSkill
- mechanical-preprocessSkill
- quality-gateSkill
- editorial-packageSkill
- humanizer-proSkill
- literary-agent-panelSkill
- manuscript-managerSkill
- narrative-foundationSkill
- book-autoSkill
- continuity-guardianSkill
- entity-trackerSkill
- reader-personaSkill
- voice-fingerprintSkill
- production-prepSkill
- prose-craftSkill
- series-architectSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 7 are distinctive, and 10 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this when the user says things like:
- Distinctive: line 35
Create durable files. Do not keep the book only in chat.
- Very specific: line 54
Run book-researcher before architecture unless user already supplied market research.
- Very specific: line 55
Run book-genesis phases 0-3 to build intake, foundation, architecture, and manuscript.
- Very specific: line 56
After first full draft or major act, run literary-agent-panel.
- Very specific: line 57
Run book-swarm-panel when the project needs many fictional readers, niche/sensitivity-risk scouting, public-opinion reaction, or …
- Very specific: line 58
Run book-genesis adversarial audit and Genesis Score.
- Very specific: line 59
Use book-editor only against specific findings.
- Very specific: line 60
Use humanizer-pro (literary register) and copy-editing after structure is stable.
- Very specific: line 61
Run literary-agent-panel and/or book-swarm-panel again after revision.
- Very specific: line 62
Run editorial-package only after manuscript passes product gates.
- Very specific: line 63
Run launch-strategy and content-strategy for public-launch readiness.
- Distinctive: line 67
Do not call a project "market-ready", "best-seller-ready", or "publication-ready" unless all gates pass or blockers are documented.
- Distinctive: line 107
write for a specific reader, not "everyone"
- Distinctive: line 108
use comp titles from the current market, not classics
- Distinctive: line 111
document risks instead of pretending certainty
- Distinctive: line 127
If user asks only for one part, run only the relevant specialist and do not force full pipeline.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Book Bestseller Studio
This is the umbrella skill for creating a complete book at market level. It does not replace book-genesis or the portable book-genesis-core core; it coordinates the specialist skills and adds commercial gates.
Use this when the user says things like:
- "create a complete book"
- "bestseller-level"
- "commercially viable book"
- "prepare for agents/editors"
- "complete book pipeline"
- "market-ready"
- "publication or launch prep"
Specialist Stack
book-genesis: canonical project pipeline, state files, chapters, audits, Genesis Score.book-researcher: genre map, comp titles, reader gaps, word count targets, nonfiction evidence.book-swarm-panel: MiroFish-style simulated reader swarms, niche-risk scouting, public-opinion tests, interviews, heatmaps, and revision tickets.literary-agent-panel: simulated agent/editor/bookseller review for market acceptance.book-editor: surgical revision by mode after evaluation.copy-editing: final language cleanup.humanizer-pro: measured, register-aware de-AI rewriting against the real human distribution (Better Humanizer). Replaces the old rule-basedhumanizer.editorial-package: logline, back-cover copy, synopsis, query letter, cover brief.launch-strategy: go-to-market, offer, launch calendar, proof-driven positioning.content-strategy: audience-building and content plan around the book.
Operating Rule
Create durable files. Do not keep the book only in chat.
Default project layout:
<project>/
PROJECT_STATE.yaml
ASSUMPTIONS.md
research/
foundation/
manuscript/
chapters/
evaluations/
delivery/
launch/Market-Level Pipeline
- Run
book-researcherbefore architecture unless user already supplied market research. - Run
book-genesisphases 0-3 to build intake, foundation, architecture, and manuscript. - After first full draft or major act, run
literary-agent-panel. - Run
book-swarm-panelwhen the project needs many fictional readers, niche/sensitivity-risk scouting, public-opinion reaction, or package-framing tests. - Run
book-genesisadversarial audit and Genesis Score. - Use
book-editoronly against specific findings. Pick mode: structural, connective, prose-texture, rag-rewrite, or factual. - Use
humanizer-pro(literary register) andcopy-editingafter structure is stable; gate withubss humanize-score <project>. - Run
literary-agent-paneland/orbook-swarm-panelagain after revision. - Run
editorial-packageonly after manuscript passes product gates. - Run
launch-strategyandcontent-strategyfor public-launch readiness.
Commercial Gates
Do not call a project "market-ready", "best-seller-ready", or "publication-ready" unless all gates pass or blockers are documented.
Gate 1: Product Fit
- clear genre/category
- current comp titles
- target reader defined
- reader promise stated in one sentence
- format and word count match category expectations
Gate 2: Manuscript Fit
- complete manuscript or explicit serial/novella positioning
- opening creates immediate reader contract
- chapter endings sustain forward motion
- weakest Genesis Score dimension is not hiding behind average score
- continuity and factual checks complete
Gate 3: Market Package
- logline
- 100-word cover copy
- 300-word editorial synopsis
- query/pitch letter
- cover brief with genre shelf fit
- author positioning
Gate 4: Launch Fit
- proof points or platform plan
- audience acquisition path
- content angles
- launch calendar
- review/ARC strategy
- retailer/category metadata assumptions
Bestseller Discipline
"Bestseller" is a positioning target, not a promise. Treat it as a standard for product, package, and launch quality:
- write for a specific reader, not "everyone"
- use comp titles from the current market, not classics
- make the first 10 pages commercially ruthless
- preserve voice while improving readability
- document risks instead of pretending certainty
- separate craft excellence from market readiness
Output Contract
For any full run, maintain:
research/market-research.mdfoundation/positioning.mdmanuscript/chapters/chapter-XX.mdevaluations/agent-panel.mdevaluations/book-swarm/<run>/SUMMARY.mdevaluations/genesis-score.mddelivery/editorial-package.mdlaunch/launch-plan.md
If user asks only for one part, run only the relevant specialist and do not force full pipeline.
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
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.

