agentleFS
jodyjdcjodyjdc/ultimate-best-seller-studio/skills/book-genesis-core/SKILL.md

book-genesis-core

Skill2 starsChanged 5 months agoMITView on GitHub

Use when the user wants the portable Book Genesis pipeline for Claude Code, Codex, Antigravity, Kimi, or another file-aware agent: intake, foundation, architecture, drafting, adversarial audit, Genesis Score, and editorial package with durable project files.

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 8 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for:

    line 12
  2. Very specific:

    Do not use the legacy V4 17-phase workflow as the default.

    line 21
  3. Very specific:

    Use references/pipeline/phases.md for the compact phase overview.

    line 52
  4. Distinctive:

    Read only the prompt for the active phase:

    line 56
  5. Very specific:

    Read PROJECT_STATE.yaml if it exists.

    line 71
  6. Very specific:

    Read ASSUMPTIONS.md if it exists.

    line 72
  7. Very specific:

    Update PROJECT_STATE.yaml after every phase, chapter block, audit, or score.

    line 74
  8. Distinctive:

    Do not skip Phase 4. Audit before final scoring.

    line 75
  9. Very specific:

    When drafting, write in chapter files under manuscript/chapters/ and keep the state synchronized.

    line 76
  10. Distinctive:

    When user feedback changes direction, record it in project files before continuing.

    line 77
  11. Distinctive:

    Prefer fewer constraints during drafting.

    line 81
  12. Distinctive:

    Use the Genesis Score floor principle: the book is only as strong as its weakest major dimension.

    line 83
  13. Distinctive:

    If a task is only editing, scoring, or packaging an existing manuscript, start from the matching phase instead of forcing a full restart.

    line 85
  14. Distinctive:

    Use these only when relevant and already available:

    line 89

≈ “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 Genesis Universal Core

Book Genesis Universal Core is Felipe's portable book-production pipeline for file-aware AI agents. It works in Claude Code, Codex, Antigravity, Kimi, and similar tools that can read project files and write artifacts.

The skill folder is still named book-genesis-core for compatibility with existing installs and slash commands. The workflow is not Codex-only. It is the canonical lightweight workflow for new runs, separate from the legacy V4/V5 multi-skill system kept elsewhere in this repository.

Use this skill for:

  • fiction, memoir, nonfiction, or hybrid book projects
  • turning a rough idea into a structured book
  • drafting full manuscripts chapter by chapter
  • auditing AI-written prose and narrative structure
  • producing Genesis Score evaluations
  • creating synopses, cover briefs, launch/editorial packages, and formatting handoff notes

Do not use the legacy V4 17-phase workflow as the default. It is copied only for historical reference in references/legacy-v4-book-genesis.md.

Core Rule

Persist important decisions to files. A Book Genesis run should leave a durable project tree, not just chat output.

Default project layout:

<project>/
  PROJECT_STATE.yaml
  ASSUMPTIONS.md
  artifacts/
  manuscript/
    chapters/
  evaluations/
  delivery/

Canonical Pipeline

Load references/pipeline/manifest.yaml before starting or advancing phases.

  1. Phase 0: Intake
  2. Phase 1: Foundation
  3. Phase 2: Architecture
  4. Phase 3: Drafting
  5. Phase 4: Adversarial Audit
  6. Phase 5: Final Score
  7. Phase 6: Editorial Package

Use references/pipeline/phases.md for the compact phase overview.

Phase References

Read only the prompt for the active phase:

  • Intake: references/prompts/intake.md
  • Foundation: references/prompts/foundation.md
  • Architecture: references/prompts/architecture.md
  • Drafting: references/prompts/drafting.md
  • Adversarial Audit: references/prompts/adversarial-audit.md
  • Final Score: references/scoring/genesis-score.md
  • Editorial Package: references/prompts/editorial-package.md

references/prompts/orchestrator.md contains the portable orchestration rules.

Operating Loop

  1. Identify or create the project directory.
  2. Read PROJECT_STATE.yaml if it exists. If not, initialize it from the manifest phases and user idea.
  3. Read ASSUMPTIONS.md if it exists. If not, create it and mark inferred assumptions clearly.
  4. Load the current phase prompt and produce only that phase's required outputs.
  5. Update PROJECT_STATE.yaml after every phase, chapter block, audit, or score.
  6. Do not skip Phase 4. Audit before final scoring.
  7. When drafting, write in chapter files under manuscript/chapters/ and keep the state synchronized.
  8. When user feedback changes direction, record it in project files before continuing.

Quality Policy

  • Prefer fewer constraints during drafting; evaluate and repair afterward.
  • Separate drafting, audit, scoring, and editorial judgment in the workflow.
  • Use the Genesis Score floor principle: the book is only as strong as its weakest major dimension.
  • For Portuguese books, write artifacts and prose in Portuguese unless the user requests otherwise.
  • If a task is only editing, scoring, or packaging an existing manuscript, start from the matching phase instead of forcing a full restart.

Complementary Skills

Use these only when relevant and already available:

  • copy-editing for prose-level cleanup
  • humanizer-pro for measured, register-aware de-AI rewriting (Better Humanizer; use the literary register for fiction)
  • launch-strategy or content-strategy for go-to-market assets
  • imagegen or cover-specific workflows for cover ideation

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.