modellix-comic
/modellix-comic
Planuje prompty do komiksu edukacyjnego, wiedzowego, biograficznego lub czterokadrowego: poleca styl, ton i układ, potwierdza liczbę stron, proporcje i język, ustala obsadę i przekazuje każdą stronę do modellix-design.
- Autor
- Modellix ↗
- Repozytorium
- modellix-skill ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 22.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 7
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 22.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Planuje prompty do komiksu edukacyjnego, wiedzowego, biograficznego lub czterokadrowego: poleca styl, ton i układ, potwierdza liczbę stron, proporcje i język, ustala obsadę i przekazuje każdą stronę do modellix-design.
Wyzwalacze z opisu
Oryginalny opis (EN)
Plan prompts for a knowledge comic, educational comic, biography comic, tutorial comic, concept story, or four-panel strip. Use this skill whenever the user asks for 知识漫画, 教育漫画, 传记漫画, 四格漫画, or a comic that explains an idea — even if they only say "turn this into a comic." Recommend art, tone, and layout or a preset, confirm page count, aspect, language, and text level, lock the cast, then hand each page to modellix-design. Skip infographics, article covers, in-article illustration sets, social cards, posters, and requests that only need an already finished prompt executed.
Jak działa
- Route the request
- Plan the comic
- Brief
- Revision
Podgląd SKILL.md
--- name: modellix-comic description: Plan prompts for a knowledge comic, educational comic, biography comic, tutorial comic, concept story, or four-panel strip. Use this skill whenever the user asks for 知识漫画, 教育漫画, 传记漫画, 四格漫画, or a comic that explains an idea — even if they only say "turn this into a comic." Recommend art, tone, and layout or a preset, confirm page count, aspect, language, and text level, lock the cast, then hand each page to modellix-design. Skip infographics, article covers, in-article illustration sets, social cards, posters, and requests that only need an already finished prompt executed. license: MIT compatibility: No external tools required; pairs with the modellix-design skill for image execution. metadata: author: Modellix version: "1.0.0" modellix-hermes-tags: comic,knowledge,storyboard,prompt-engineering,modellix --- # Modellix Comic Turn a source into a storyboard and one prompt per page. This skill plans the comic. `modellix-design` generates each image. Do not submit, poll, download, authenticate, or inspect model schemas here. Do not run the Modellix CLI. Do not recommend a model, a provider, or a slug. When the user wants the pages made, finish the brief first and then hand the prompts to `modellix-design` in order. A structured infographic belongs to `modellix-infographic`. An article cover with no named network belongs to `modellix-cover-image`. A set of illustrations placed through an article belongs to `modellix-article-illustrator`. A card for a named network belongs to `modellix-social-card`. A poster, product shot, or single illustration belongs to `modellix-image-prompt-engineering`. A commerce UGC video belongs to `modellix-ecomm-ugc-video`. Files already on disk belong to `modellix-ffmpeg` or `modellix-moviepy`. ## Route the request Use this skill when the user wants a new comic that explains something: a tutorial, a technical idea, a biography, a concept story, or a four-panel strip. Ask once for the source when the user names the format but not the subject. Do not invent a title, a date, a quotation, or a statistic to fill an empty request. Skip or keep the pass short when: - The user already supplied finished page prompts and asked only to run them. Pass those prompts to `modellix-design` in the order given. - The request is one comparison, sequence, or metric board with no story. Use `modellix-infographic`. - The request is one article, blog, or newsletter cover. Use `modellix-cover-image`. - The request is a set of illustrations placed through an article, with no comic pages. Use `modellix-article-illustrator`. - The request names a network and a card, cover, thumbnail, or carousel. Use `modellix-social-card`. - The request is a poster, product shot, or single illustration. Use `modellix-image-prompt-engineering`. - The request is a commerce UGC video that still needs a shot plan. Use `modellix-ecomm-ugc-video`. - The request is video editing, credentials, task status, or a download. ## Plan the comic Read `references/selection.md` to recommend the style. Read `references/styles.md` for what those names look like, and `references/presets.md` when a preset is chosen. Read `references/storyboard.md` before writing a prompt. 1. Copy the facts that must survive. Keep names, dates, and quotations the source actually contains. Drop credentials, tokens, and secrets. Do not add a claim the source does not contain. 2. State the core message in one sentence. Decide what to keep, simplify, and leave out. A concept becomes a prop, an action, or a place, not a lecture. 3. Recommend one preset, or one art style, tone, and layout. Give a one-line reason from the source. Also recommend the page count, aspect, on-image language, and text level. Language follows the source unless the user names another. A four-panel strip is one page at 3:4. A webtoon is 9:16. Other comics default to 3:4. Recommend a cover plus at most six story pages unless the user already named a count. Do not plan a long serial by default. 4. A choice the user already named is the confirmation. If any of preset or art/tone/layout, page count, aspect, language, or text level is still open, ask once for the open set and wait. "Use the recommendation" is a confirmation. Do not write prompts before that. 5. Define the cast in words: role, age range, face, hair, build, costume, and two or three color names. Repeat that same lock in every page prompt. Use original characters. Do not borrow a named copyrighted mascot. A historical person is described by era, role, and costume in the chosen art style, not as a photographic portrait. 6. When more than one page shares recurring characters, write a character-sheet prompt first: front view, three-quarter view, and a few expressions on a plain background. A four-panel strip and any other single page skip the sheet. The brief tells `modellix-design` to generate the sheet first and pass that saved image as a reference on every later page. This skill does not upload files. 7. Write one prompt per page, in reading order. Describe the panel grid, the action, and the cast lock. `bubbles` quotes only short lines from the source or the user, and tells the model to copy them and add no title, logo, watermark, or extra claim. `silent` puts no words in the image and lists the lines beside that page. Do not hand those lines to `modellix-ffmpeg` or `modellix-moviepy`. When the user supplies reference images, name each path and one usage: direct, style, or palette. Describe the concrete elements to keep. Until the open choices are confirmed, return the recommendation and the facts you will keep, and leave every prompt empty. ## Brief Return this brief: ```text Comic brief - Title / core message: - Preset or art / tone / layout: - Pages / aspect: - On-image language / text level: - Cast: - References: none | path / usage - Character sheet prompt: omitted | prompt - Pages: N. role / exact text / prompt - Next step: stop after prompts | pass prompts to modellix-design in order - Model: <only a slug the user already named | omitted> ``` Leave `Model` blank unless the user already named a slug. Do not browse the catalog from this skill. If the user asked only for prompts, stop after the brief. If the original request asked for the comic, pass the prompts to `modellix-design` in this order: character sheet when present, then the cover, then the story pages. That skill asks for a model and owns schema validation, credentials, paid submission, waiting, and download. Each page is a separate image. ## Revision When a generated page misses, change the prompt and return a new brief: - Garbled or invented words: shorten the quoted line, or switch that page to `silent`. Do not paint text over the bitmap. - A character changed face or costume: restate the cast lock and require the character-sheet image as a reference. - A talking-heads page in a preset that forbids them: replace the panel with a prop, an action, or a place. - A photographic portrait of a historical person: restate the chosen art style and the era costume. `modellix-design` decides whether an existing task can be recovered or a new submission is appropriate.
Pliki w paczce (7)
- SKILL.md 7 KB
- skill.json 1 KB
- evals/evals.json 5 KB
- references/presets.md 3 KB
- references/selection.md 3 KB
- references/storyboard.md 4 KB
- references/styles.md 2 KB
Wersje
W bazie nie ma innych skilli o nazwie modellix-comic.
Migawka bazy z 28.10.2026 · wersja paczki 60856a613658 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100modellix-article-illustrator
Planuje prompty do zestawu ilustracji rozmieszczonych w artykule: poleca preset albo typ, styl i paletę, potwierdza gęstość, proporcje i język, pisze prompt dla każdej ilustracji i przekazuje do modellix-design. - 100modellix-cover-image
Planuje jeden prompt do okładki artykułu, bloga lub newslettera: poleca typ, paletę, renderowanie, ilość tekstu, nastrój i krój, potwierdza je, cytuje tytuł źródła i przekazuje generowanie do modellix-design. - 95argentos-baoyu-comic
Tworzy edukacyjne komiksy wiedzy w różnych stylach graficznych, z rozpisanymi kadrami i sekwencyjnie generowanymi obrazami. - 95community-baoyu-comic
Tworzy edukacyjne komiksy wiedzy w różnych stylach: szczegółowe kadry, biografie, poradniki i komiksy w stylu Logicomix. - 100baoyu-comic
Tworzy oryginalne komiksy edukacyjne w wielu stylach graficznych, z rozplanowanymi kadrami i wsadowym generowaniem obrazów, w tym komiksy biograficzne i tutorialowe. - 100baoyu-comic
Tworzy oryginalne komiksy edukacyjne w różnych stylach graficznych i tonach, ze szczegółowym układem kadrów i sekwencyjnym generowaniem obrazów, na przykład biograficzne lub w stylu Logicomix.