Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Baoyu Article Illustrator

Analyzes an article, picks the spots that need visuals, and generates a consistent image set using a Type × Style × Palette system before inserting them back into the text.

Image & VideoIntermediate★ 26,102⑂ 2,884AI score 9/10Last updated: Sep 10, 2026

What it does

  • Reads your article and classifies content type (technical / tutorial / methodology / narrative), extracts 2–5 core arguments, and marks where illustrations actually add value.
  • Locks visual consistency with three dimensions: Type (infographic, scene, flowchart, comparison, framework, timeline) × Style (notion, warm, minimal, blueprint, watercolor...) × Palette (macaron, warm, neon), plus one-flag presets.
  • Requires an outline.md and one prompt file per image (prompts/NN-{type}-{slug}.md) to be written before any render, so runs are reproducible and backend-agnostic.
  • Resolves the image backend by priority (Codex imagegen, Cursor GenerateImage, other runtime-native tools, then baoyu-image-gen) and renders in batches of 4 by default.
  • Inserts Markdown image references after the right paragraphs, and enforces hard rules: no SVG/HTML substitutes for raster output, no bitmap over-painting to fix broken text — regenerate from a corrected prompt instead.

Who it's for

  • Bloggers and newsletter writers who need illustrations often and want a stable look across posts.
  • Content teams maintaining a single visual identity across many articles.
  • Users already inside Codex/Cursor or running an image-generation skill.
  • Anyone who wants a durable prompt archive for later edits and regeneration.

Examples

  1. Point it at a Markdown file and say "illustrate this article" — it analyzes, asks up to four setup questions (preset, density, style, palette), writes prompts, then generates into imgs/ and inserts the images.
  2. Run --type infographic --style vector-illustration --palette macaron on a data-heavy post to get 3–5 infographics whose labels carry the article's real numbers and terms.
  3. Pass brand assets with --ref so composition and palette match your existing visuals; if one image renders bad text, it writes a new prompt file and output path while keeping the flawed candidate for comparison.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/JimLiu/baoyu-skills/HEAD/skills/baoyu-article-illustrator/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

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.
  2. Clone the repo: git clone https://github.com/JimLiu/baoyu-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r baoyu-skills/skills/baoyu-article-illustrator ~/.claude/skills/
  5. (Recommended) Make sure a raster backend exists. If you're not in Codex (imagegen) or Cursor (GenerateImage), also copy the baoyu-image-gen skill from the same repo.
  6. Restart Claude Code and ask: "illustrate this article" with the file path.
  7. On the first run it walks you through EXTEND.md setup (output directory, default style/palette, language, preferred backend); answer once and later runs reuse it.
View source on GitHub ↗License: MIT