agentleFS
appleweipingappleweiping/AGENT_RESOURCE/skills/vipin/literature-to-manga/SKILL.md

literature-to-manga

Skill78 starsChanged 25 days agoApache-2.0View on GitHub

Convert selected prose, novel, biography, history, or text-archive works into manga adaptation packages. Use when asked to pick books from a local literature repository, assess manga adaptability, extract plots and characters, design chapters, write manga panel scripts, create storyboard briefs, or generate visual prompt packs for comic adaptation.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 6 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to turn a source work or a folder of candidate books into a manga adaptation package.

    line 10
  2. Very specific:

    If no path is provided, use $LITERATURE_BOOKS_DIR.

    line 17
  3. Distinctive:

    Prefer works with visible scene changes, strong conflict, recurring cast, and clear episodic arcs.

    line 24
  4. Very specific:

    Use assets/templates/candidate-dossier.md for shortlist output.

    line 25
  5. Very specific:

    Read references/source-handling.md when file formats, encoding, or archive extraction is uncertain.

    line 26
  6. Very specific:

    Read references/adaptation-workflow.md for the scoring rubric and adaptation phases.

    line 31
  7. Very specific:

    Read references/visual-style-taxonomy.md before choosing art direction or image prompt language.

    line 36
  8. Distinctive:

    Write chapter scripts and storyboard briefs.

    line 38
  9. Very specific:

    Read references/manga-script-format.md for panel syntax and pacing rules.

    line 42
  10. Distinctive:

    Create one JSONL row per key panel or character sheet prompt.

    line 45
  11. Distinctive:

    Keep character identity, style, composition, lighting, and negative constraints explicit.

    line 46
  12. Distinctive:

    Check source fidelity, continuity, character consistency, panel readability, pacing, and prompt reuse.

    line 50
  13. Distinctive:

    If the user asks only to pick books, stop after the candidate dossier and recommendations.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Literature To Manga

Overview

Use this skill to turn a source work or a folder of candidate books into a manga adaptation package. Default source archive: the folder in $LITERATURE_BOOKS_DIR, if set.

The default output is an adaptation dossier, manga bible, chapter/page/panel script, storyboard brief, and image prompt pack. Copyright is not a hard gate by default, but every package must include source attribution and a publication-risk note.

Workflow

  1. Locate the archive or source file.
    • If no path is provided, use $LITERATURE_BOOKS_DIR; if that is not set either, ask the user where the books are.
    • For candidate discovery, run scripts/inventory_books.py.
    • For source extraction, run scripts/extract_text.py.
    • For long texts, run scripts/chunk_source.py before deep adaptation.
  2. Inventory and rank candidates.
    • Score narrative clarity, character strength, scene density, visual potential, length fit, and adaptation difficulty.
    • Prefer works with visible scene changes, strong conflict, recurring cast, and clear episodic arcs.
    • Use assets/templates/candidate-dossier.md for shortlist output.
    • Read references/source-handling.md when file formats, encoding, or archive extraction is uncertain.
  3. Build the adaptation brief.
    • Define premise, audience, format, tone, season/chapter target, transformation strategy, and source-fidelity stance.
    • Use assets/templates/adaptation-brief.md.
    • Read references/adaptation-workflow.md for the scoring rubric and adaptation phases.
  4. Build the manga bible.
    • Include logline, world rules, cast, character designs, relationships, plot arcs, recurring locations, visual motifs, and continuity rules.
    • Use assets/templates/manga-bible.md.
    • Read references/visual-style-taxonomy.md before choosing art direction or image prompt language.
  5. Write chapter scripts and storyboard briefs.
    • Convert prose beats into pages and panels, not long narration.
    • Each panel needs shot type, visible action, dialogue/caption text, mood, and continuity notes.
    • Use assets/templates/chapter-script.md.
    • Read references/manga-script-format.md for panel syntax and pacing rules.
  6. Generate image prompt packs.
    • Create one JSONL row per key panel or character sheet prompt.
    • Keep character identity, style, composition, lighting, and negative constraints explicit.
    • Use assets/templates/storyboard-prompts.jsonl.
  7. Run adaptation QA.
    • Check source fidelity, continuity, character consistency, panel readability, pacing, and prompt reuse.
    • Mark invented material clearly.
    • Include a publication-risk note when the source is not confirmed public domain or licensed.

Output Contract

For a full package, create or return:

  • candidate-dossier.md
  • adaptation-brief.md
  • manga-bible.md
  • chapter-01-script.md
  • storyboard-prompts.jsonl
  • qa-notes.md

If the user asks only to pick books, stop after the candidate dossier and recommendations. If the user already picked a work, skip broad inventory and start with source extraction plus the adaptation brief.

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.