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

Baoyu Article Illustrator

Analyzes your article, decides where illustrations belong, and generates a visually consistent set of images via a Type × Style × Palette system.

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

What it does

  • Reads a Markdown file (or pasted text), classifies the content type (technical / tutorial / methodology / narrative) and extracts 2–5 core arguments.
  • Picks the positions where an image genuinely adds value and writes an outline.md with position, purpose, visual content, and filename for each illustration.
  • Combines three dimensions — Type (infographic, scene, flowchart, comparison, framework, timeline) × Style (notion, warm, minimal, blueprint, watercolor, elegant) × Palette (macaron, warm, neon) — so every image in the article shares one visual language.
  • Hard requirement: each image's final prompt is saved to prompts/NN-{type}-{slug}.md before rendering, giving you a reproducibility record and letting you swap image backends later.
  • Renders in batches (default 4 in parallel), then inserts ![](imgs/...) after the right paragraphs and prints a completion summary.
  • Explicitly forbids painting over bitmaps to fix broken text — bad text means a new prompt and a new file, so flawed candidates stay comparable.

Who it's for

  • Bloggers, newsletter writers, and docs authors tired of sourcing images by hand.
  • Content teams that need a consistent visual tone across many posts.
  • Developers and educators who want abstract concepts turned into diagrams.
  • Anyone with an available raster backend: Codex imagegen, Cursor GenerateImage, or the baoyu-image-gen skill.

Examples

  1. Technical post — "illustrate this article --type infographic --style notion" → 3–5 infographics whose labels carry the actual metrics and terms from your text, inserted inline.
  2. Step-by-step tutorial — --type flowchart --preset edu-visual with per-section density gives every section its own process diagram.
  3. Essay / narrative — --type scene --style watercolor --palette macaron at minimal density produces just two mood illustrations for the opening and closing.
  4. Brand-matched output — pass --ref brand-guide.png so generated art follows your palette and composition references.

· · · 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-article-illustrator folder from the GitHub repo JimLiu/baoyu-skills into my ~/.claude/skills/baoyu-article-illustrator/.
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-article-illustrator ~/.claude/skills/

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

  1. Open a terminal (Terminal on macOS/Linux, WSL or Git Bash on Windows).
  2. Clone the skill repository: 
    git clone https://github.com/JimLiu/baoyu-skills.git
  3. Create the Claude Code skills folder and copy this skill in: 
    mkdir -p ~/.claude/skills
cp -r baoyu-skills/skills/baoyu-article-illustrator ~/.claude/skills/
  4. Make sure a raster image backend is reachable. Runtime-native tools (imagegen in Codex, GenerateImage in Cursor) are used automatically; otherwise install the companion skill: 
    cp -r baoyu-skills/skills/baoyu-image-gen ~/.claude/skills/
  5. Restart Claude Code and confirm baoyu-article-illustrator appears in your skill list.
  6. On the first run the skill launches its EXTEND.md first-time setup: choose an output directory (imgs-subdir is a safe default), default style, language, and preferred image backend.
  7. Ask it to work on a file, e.g. "illustrate my-post.md". Answer the confirmation questions (type / density / style) and generation begins.
  8. To bypass confirmation, add wording like "just generate it, skip confirmation" to your request.
View source on GitHub ↗License: MIT