Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Baoyu Knowledge Comic Creator

Turns a topic or article into a full educational comic — storyboard, consistent characters, generated pages, and a merged PDF.

Image & VideoIntermediate★ 24,749⑂ 2,764AI score 8/10Last updated: Jul 4, 2026

What it does

Give it a topic, a person, or a source document and it runs the whole pipeline: content analysis → storyboard with panel breakdown → character definitions plus a character reference sheet → per-page image prompts → rendered pages → merged PDF.

  • 6 art styles: ligne-claire, manga, realistic, ink-brush, chalk, minimalist
  • 7 tones: neutral, warm, dramatic, romantic, energetic, vintage, action
  • 5 presets with extra rules: ohmsha, wuxia, shoujo, concept-story, four-panel
  • Every prompt is written to prompts/NN-page-*.md first, so runs are reproducible and backends are swappable
  • The character sheet is passed as a reference image to keep recurring characters on-model; user-supplied refs can guide style or palette
  • Partial runs (--storyboard-only, --prompts-only, --images-only, --regenerate 3,5) and batched generation (default 4 pages at a time)
  • Explicit rule against patching text by painting over bitmaps — flawed pages are regenerated, not retouched

Who it's for

  • Educators and course creators who want concepts explained as comics
  • Bloggers and newsletter writers illustrating biographies, tutorials, or ideas
  • Creators producing multi-part series that need consistent characters and style

Examples

  1. "Make a 12-page Logicomix-style comic about Alan Turing's life" → creates comic/alan-turing-bio/ with storyboard, character sheet, 12 pages, and a PDF
  2. "Summarize this blog post as a four-panel strip --art minimalist --layout four-panel" → B&W with spot color, classic setup-turn-punchline structure
  3. "Page 5's expression is off — fix the prompt and --regenerate 5" → updates only that prompt file, re-renders the page, rebuilds the PDF

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/baoyu-comic folder from the GitHub repo JimLiu/baoyu-skills into my ~/.claude/skills/baoyu-comic/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/JimLiu/baoyu-skills.git && mkdir -p ~/.claude/skills && cp -r baoyu-skills/skills/baoyu-comic ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/JimLiu/baoyu-skills.git
  3. Install the skill: mkdir -p ~/.claude/skills && cp -r baoyu-skills/skills/baoyu-comic ~/.claude/skills/
  4. Make sure a runtime for the bundled scripts exists: run bun --version; if missing, install with curl -fsSL https://bun.sh/install | bash, or rely on npx -y bun if Node.js is present.
  5. Provide one raster image backend — Codex's native imagegen, Cursor's GenerateImage, or the baoyu-image-gen skill from the same repo. Without one, the image steps will stop and ask you.
  6. Restart Claude Code and try: "create a knowledge comic about Alan Turing".
  7. On the first run a blocking setup wizard asks for art style, tone, language, and image backend, then saves them to ~/.baoyu-skills/baoyu-comic/EXTEND.md; edit that file later to change defaults.
View source on GitHub ↗License: MIT