Style Comic logo

Style Comic

Community
illodev
style-comic

Comic book style (in testing) — brush-ink outlines with variable width and tapered ends, flat print colours on newsprint, Ben-Day halftone, panels that pop in on the beat, balloons, sound effects on bursts, speed lines. Use it when asked for a comic, cartoon, pop-art, «viñetas», motion comic, onomatopoeia or panels, or when working with styles/comic/.

Overview

Publisherillodev
Repositorydrawn-by-code
Skill namestyle-comic
Stars
31
Forks
3
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by illodev on GitHub. Read the source before you install it.

Installation

Install the Style Comic AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/illodev/drawn-by-code/tree/main/.claude/skills/style-comic
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/illodev/drawn-by-code.git /tmp/drawn-by-code
mkdir -p .claude/skills
cp -r /tmp/drawn-by-code/.claude/skills/style-comic .claude/skills/style-comic
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Style Comic in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Style Comic on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Style Comic is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Style · Comic

In testing. Reference: styles/comic/template.js (look at styles/comic/review/sheet.jpg). Its first style test was a client piece and lives in the client's private repo.

Code

styles/comic/comic.js → Comic. Declare both fonts in the scene (OFL, licences in fonts/):

js
fonts: [
    { family: 'Bangers', src: 'fonts/Bangers-Regular.ttf' },
    { family: 'Comic Neue', src: 'fonts/ComicNeue-Bold.ttf', descriptors: { weight: '700' } },
],
  • Time: onTwos(t) (t held on its drawing), drawing(t) (drawing number, 12 a second).
  • Ink: ink(g, pts, { w, taper, wobble, light, closed, smooth, seed, color }) is a filled brush line that swells and tapers; shape(g, pts, { fill, w, shade, light, seed }) fills, runs shade(g, path) clipped inside, then inks the outline. Paths: curve, resample, pathOf, ellipse, rect, starPts, and lobes(circles, cx, cy), the outline of a union of circles (clouds, bushes, round bodies).
  • Halftone: dots(g, path, { color, spacing, r, anchor }) (Ben-Day, tile built at output resolution); halftone(g, path, { color, spacing, r0, r1, dir, box }) (graded dots for round forms and skies).
  • Page: paper(g, env, { bleed }) (newsprint, cached) and grainPost(ctx, env) in post.
  • Panels: panel(g, rect, drawFn, { border, bg }) clips the art and rules the border; enter(t, at, dur, from) is the pop-in on the beat (overshoot, on twos).
  • Lettering: letter (balloon text, upper case), balloon({ kind: 'speech' | 'thought' | 'shout', tail, text }), sfx(g, text, x, y, { size, fill, shade }) (extruded, outlined, each letter tilted and growing), burst.
  • Motion: speedLines (focus lines to a point), motionLines (streaks trailing a move).
  • Hands: hand(g, pose, size, { side, fill }), a cartoon hand (thumb + three fingers) in one skin, wrist at the origin pointing up. Poses open (back to the camera), backGrip (holding a sheet from the camera's side: the backs of three fingers over it, the thumb hidden behind), thumbFront (the owner's view of a sheet held at its bottom edge). Drawn as a right hand; side: 'left' mirrors it.
  • Tubes (limbs, handles): a wide ink line with a narrower colour line on top (the template's mug handle, limb in any puppet).

Style rules

  • Palette (Comic.COL): page #f4ecd6, deep page #e7d9b8, white #fffaf0, ink #1c1a20, red #dd3b2d, yellow #f6c536, blue #2e67ae, sky #8fc9e3, green #4f9d63, orange #f28a2e, pink #ee8fa6. Ink is never pure black and the page never pure white. A character keeps its own brand colour; everything else comes from the palette.
  • Line: brush ink with a varying width; open strokes taper; closed shapes carry the heavy side away from the light (the light comes from the top left: light: [0.55, 0.85]). Widths in a 900-wide frame: characters 6–8, props 3.5–5, panel borders 7, details 2.5–3.5. Each piece has a fixed seed: nothing boils.
  • Colour: flat fills. Shading only as Ben-Day dots (flat or graded) or a hard cel shape, never a soft gradient. Dots on a moving piece are drawn in its local transform so they travel with it.
  • One-skin silhouettes: a form made of several pieces (a hand) inks every piece first and fills every piece on top, so only the union's silhouette keeps its line.
  • Panels: ruled borders of even width, the page as gutter. They pop in on the beat with a small overshoot and read left→right, top→bottom. A panel is a moment: once its beat has passed it holds (settles) instead of replaying its action. Balloons may break a border.
  • Camera (motion comic): start inside the first panel so it fills the frame (the hook), pull back to the page on a beat, a gentle push at the end. Camera moves are smooth; the drawings change on twos. The final page holds as a poster.
  • Lettering: Bangers for sound effects and stamps (extruded, outlined, sitting on a burst); Comic Neue Bold upper case in balloons; a document's own text in Comic Neue.
  • Balloons: the tail points at the speaker from the free side. A thought bubble's trail never runs over a face (its circles read as spots): use a speech balloon with «…».
  • Marks (motion lines, impact ticks) trail behind a move or sit at the ends of a label: never across what is held and never across printed text.
  • Hands: cartoon, thumb + three fat round fingers; lines only between pressed fingers and at a bend; no nails. Right side and right view as the hands skill says.
  • Forbidden: soft gradients, pure black or white, lines that boil, anything crossing text, hands through what they hold.

Style checklist

  • Does every outline swell or taper, and is every frame's ink identical where the piece didn't move?
  • Is all shading dots or cel, with no gradient?
  • Does each panel read alone and in order, and hold once its beat has passed?
  • Does any mark, tick, trail or balloon cross printed text or a face?
  • Every hand: right side, right view, one skin, in front of or behind what it holds (never through)?
  • Vertical: SFX, balloons and text inside the safe zone (top 150 / bottom 250 px at 1080×1920)?
  • Static panel backgrounds cached as sprites at the camera's largest zoom (< 150 ms/frame warm)?

Lessons

  • 2026-09-26 · first style test · A vertical page of stacked panels is mostly empty until the last panel lands: start the camera inside the first panel (it fills the frame and is the hook) and pull back to the page on the beat.
  • 2026-09-26 · first style test · Pupils that look up vanish under a heavy lid: lift the lid a little whenever the eyes go up.
  • 2026-09-26 · first style test · An arm raised from the middle of a round body, elbow inside it, reads as a noodle: attach it at the side, drawn behind the body, with the elbow outside.
  • 2026-09-26 · first style test · The other arm resting reads as a mug handle unless it is akimbo in two passes: upper arm behind the body, forearm and hand in front.
  • 2026-09-26 · first style test · A thumb seen from its owner's eyes reads as a pointing finger until the mound of the hand shows under the held edge, with the lines of the curled fingers.
  • 2026-09-26 · first style test · Nails on the backs of cartoon fingers read as spots at this size: leave them out.
  • 2026-09-26 · first style test · Impact ticks above and below a label crossed the text next to it: put them at the label's ends.
  • 2026-09-26 · first style test · Graded halftone is drawn dot by dot: caching the static panel backgrounds at the camera's largest zoom took a page from 223 to 144 ms/frame.

Frequently asked questions

What does the Style Comic AI skill do?

Comic book style (in testing) — brush-ink outlines with variable width and tapered ends, flat print colours on newsprint, Ben-Day halftone, panels that pop in on the beat, balloons, sound effects on bursts, speed lines. Use it when asked for a comic, cartoon, pop-art, «viñetas», motion comic, onomatopoeia or panels, or when working with styles/comic/.

Why use Style Comic on TypingMind?

Because you install it once and use it with any model. Style Comic is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Style Comic in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/illodev/drawn-by-code/tree/main/.claude/skills/style-comic. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Style Comic?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Style Comic?

As many as you like. As long as a model supports skills, you can use Style Comic with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Style Comic AI skill free?

It is published on GitHub by illodev. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇