agentleFS
Sign inStart free
jodyjdcjodyjdc/ultimate-best-seller-studio/skills/optional/book-auto/SKILL.md

book-auto

Skill2 starsChanged 5 months agoMITView on GitHub

One-command book generation. Give it an idea, get a publish-ready book. Dispatches the book-orchestrator agent which runs the entire 17-phase pipeline autonomously, pausing only at 3 human checkpoints.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    When this skill is invoked, IMMEDIATELY dispatch the book-orchestrator agent:

    line 47
  2. Distinctive:

    Do NOT add commentary. Do NOT ask questions.

    line 55
  3. Very specific:

    All books are created at: ~/Desktop/livros/{slug}/

    line 61

≈ “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

/book-auto — One Command, One Book

What This Does

You give an idea. You get a book. That's it.

This skill dispatches the book-orchestrator agent which runs the entire Book Genesis V4 pipeline autonomously:

  1. Market research
  2. Reader personas
  3. Narrative foundation (characters, outline, theme)
  4. Voice DNA (per-character voice specs)
  5. >>> CHECKPOINT 1: You approve the foundation <<<
  6. Entity state initialization (builds ENTITY_STATE.yaml from foundation)
  7. Continuity check (outline)
  8. Writing all chapters (with dialogue polish, hooks, chaos, entity state update per batch, mechanical cleanup, evaluation, quality gate — all automatic)
  9. Full-manuscript evaluation
  10. Revisions
  11. Entity state update (tracks revisions)
  12. Continuity audit (full manuscript)
  13. >>> CHECKPOINT 2: You approve the manuscript <<<
  14. Editorial package (logline, synopsis, query letter, cover brief)
  15. Production prep (proofreading, formatting)
  16. >>> CHECKPOINT 3: Book delivered <<<

Usage

/book-auto [language] [idea]

Examples:

/book-auto pt-br thriller sobre ex-policial do CORE vingando a família assassinada por milícia
/book-auto en literary fiction about a quantum physicist losing her memory
/book-auto pt-br autoficção sobre burnout de dev em startup brasileira
/book-auto en dark romance between a hitman and a federal agent

How To Execute

When this skill is invoked, IMMEDIATELY dispatch the book-orchestrator agent:

Agent tool:
  subagent_type: book-orchestrator
  prompt: "Create a book from this idea: {user's full input including language and idea}. Run the full pipeline autonomously. Only pause at the 3 checkpoints."

Do NOT add commentary. Do NOT ask questions. Just dispatch.

The orchestrator will run for up to 200 turns, creating the entire book pipeline autonomously. It will return to the user at the 3 checkpoints for approval.

Project Location

All books are created at: ~/Desktop/livros/{slug}/

The slug is auto-generated from the title (lowercase, hyphens, no accents).

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