agentsclimarketplace

Autonovel genre pack

Skill DukeTwoCan/autonovel-agent-skills/skills/creative/autonovel-genre-pack

Collaboration-first Agent Skills pipeline for planning, drafting, revising, reviewing, and exporting long-form fiction.

Install
npx -y skills add DukeTwoCan/autonovel-agent-skills --skill autonovel-genre-pack

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 21 days oldThe repository was created 21 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when creating, extending, or validating AutoNovel genre packs. Do not use for drafting, evaluating, or generating novels.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.9 KB, as published. Nobody here has run it

AutoNovel Genre Pack Authoring

Create or revise data-driven genre packs. This skill is not invoked during novel generation.

Workflow

Hermes supplies ${HERMES_SKILL_DIR} as this skill's directory. Outside the Hermes harness, run the repository-relative commands in ../autonovel/genres/AUTHORING.md from the repository root.

  1. Read ../autonovel/genres/AUTHORING.md completely. Use its category decision guide, manifest contract, file responsibilities, size targets, combination tests, and definition of done.
  2. Choose one stable kebab-case ID, one category, and only the task files the pack genuinely needs. Accepted scaffold file IDs are contract, world, characters, beats-primary, beats-modifier, drafting, slop, guardrails, and patterns.
  3. If the pack does not exist, scaffold it before writing content:
    python ${HERMES_SKILL_DIR}/../autonovel/lib/genre_pack.py scaffold --id <pack-id> --category <category> --files <comma-separated-file-ids> --genres-root ${HERMES_SKILL_DIR}/../autonovel/genres
    
    Never scaffold over an existing pack. Extend its manifest and files directly instead.
  4. Replace template comments with pack-specific rules. Keep universal craft in ../autonovel/references/; do not duplicate it in a pack.
  5. Declare tags, aliases, dependencies (includes), conflicts, beat capability, sections, and optional patterns in manifest.json.
  6. Validate the pack and its dependency graph:
    python ${HERMES_SKILL_DIR}/../autonovel/lib/genre_pack.py validate --pack <pack-directory> --genres-root ${HERMES_SKILL_DIR}/../autonovel/genres
    
  7. Inspect task paths and estimated context cost:
    python ${HERMES_SKILL_DIR}/../autonovel/lib/genre_pack.py inspect --pack <pack-id> --genres-root ${HERMES_SKILL_DIR}/../autonovel/genres
    
  8. Dry-run a synthetic profile through compilation:
    python ${HERMES_SKILL_DIR}/../autonovel/lib/genre_resolver.py compile --state <synthetic-state.json> --task all --genres-root ${HERMES_SKILL_DIR}/../autonovel/genres --workspace <temporary-workspace>
    
    Confirm selection, primary beats, required sections, optional omissions, and conflicts behave as intended.
  9. Run focused tests before declaring the pack complete:
    python -m pytest tests/test_genre_pack.py tests/test_genre_registry.py tests/test_genre_resolver.py tests/test_genre_compile.py tests/test_genre_patterns.py tests/test_genre_integration.py -q
    

Require successful validation, inspection, dry-run compilation, and focused pytest. Report the pack path, selected tasks, token estimates, and test result.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.