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.
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- beta-readerSkill
- book-bestseller-studioSkill
- book-editorSkill
- 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
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
- Distinctive: line 12
Use this skill for:
- Very specific: line 21
Do not use the legacy V4 17-phase workflow as the default.
- Very specific: line 52
Use references/pipeline/phases.md for the compact phase overview.
- Distinctive: line 56
Read only the prompt for the active phase:
- Very specific: line 71
Read PROJECT_STATE.yaml if it exists.
- Very specific: line 72
Read ASSUMPTIONS.md if it exists.
- Very specific: line 74
Update PROJECT_STATE.yaml after every phase, chapter block, audit, or score.
- Distinctive: line 75
Do not skip Phase 4. Audit before final scoring.
- Very specific: line 76
When drafting, write in chapter files under manuscript/chapters/ and keep the state synchronized.
- Distinctive: line 77
When user feedback changes direction, record it in project files before continuing.
- Distinctive: line 81
Prefer fewer constraints during drafting.
- Distinctive: line 83
Use the Genesis Score floor principle: the book is only as strong as its weakest major dimension.
- Distinctive: line 85
If a task is only editing, scoring, or packaging an existing manuscript, start from the matching phase instead of forcing a full restart.
- Distinctive: line 89
Use these only when relevant and already available:
≈ “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.
Files
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.
- Phase 0: Intake
- Phase 1: Foundation
- Phase 2: Architecture
- Phase 3: Drafting
- Phase 4: Adversarial Audit
- Phase 5: Final Score
- 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
- Identify or create the project directory.
- Read
PROJECT_STATE.yamlif it exists. If not, initialize it from the manifest phases and user idea. - Read
ASSUMPTIONS.mdif it exists. If not, create it and mark inferred assumptions clearly. - Load the current phase prompt and produce only that phase's required outputs.
- Update
PROJECT_STATE.yamlafter every phase, chapter block, audit, or score. - Do not skip Phase 4. Audit before final scoring.
- When drafting, write in chapter files under
manuscript/chapters/and keep the state synchronized. - 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-editingfor prose-level cleanuphumanizer-profor measured, register-aware de-AI rewriting (Better Humanizer; use theliteraryregister for fiction)launch-strategyorcontent-strategyfor go-to-market assetsimagegenor cover-specific workflows for cover ideation
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.

