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

Baoyu Infographic Generator

Turns any content into a publication-ready infographic by combining 21 layout types with 22 visual styles.

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

What it does

Takes raw content — an article, a report, pasted notes — and walks it through a full infographic pipeline.

  • Analyze: detects topic, data type, complexity, tone and audience, saved to analysis.md
  • Structure: builds title, learning objectives, per-section key concepts, labels and visual elements in structured-content.md, preserving source data verbatim (and stripping any secrets/API keys)
  • Recommend: proposes 3–5 layout × style combos from 21 layouts (timeline, binary comparison, bento grid, iceberg, funnel, subway-style map, dense modules…) and 22 styles (craft-handmade, claymation, cyberpunk neon, chalkboard, pixel art, Morandi journal…)
  • Hard confirmation gate: nothing is rendered until you approve combo, aspect ratio, language and image backend (unless you pass --no-confirm)
  • Prompt file as record: the final prompt is written to prompts/infographic.md so runs are reproducible and backends are swappable
  • Render: auto-selects an available raster backend (Codex imagegen, Cursor GenerateImage, baoyu-image-gen…). It explicitly refuses to fake images with SVG/HTML and never paints over bad text — it regenerates from a corrected prompt instead.

Who it's for

  • Content creators who need summary visuals for blogs, newsletters and social posts
  • Teachers and students building concept maps, learning roadmaps, process diagrams
  • Marketers and PMs who need comparison charts or KPI dashboard visuals
  • Solo builders who want consistent-looking graphics without touching a design tool

Examples

  1. Long report → tall dense poster: "make a high-density-info graphic from this PDF" → recommends dense-modules + morandi-journal at 9:16, confirms, then renders
  2. Option A vs Option B: "infographic of the pros and cons of both plans" → binary-comparison + corporate-memphis at 16:9, ready to drop into a deck
  3. On-brand output: --ref brand.png --layout bento-grid --style craft-handmade extracts the palette from your reference image and applies it to the overview graphic

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

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

  1. Open a terminal (Terminal on macOS, WSL or Git Bash on Windows).
  2. Clone the repository: git clone https://github.com/JimLiu/baoyu-skills.git
  3. Create the skills folder if needed: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r baoyu-skills/skills/baoyu-infographic ~/.claude/skills/
  5. Verify that the references/ subfolders (layouts, styles, config) came along — without them the skill can't load layout/style definitions.
  6. Set up an image backend. If you're in Codex (imagegen) or Cursor (GenerateImage), it's already there; otherwise install the baoyu-image-gen skill the same way.
  7. Restart Claude Code and ask something like "create an infographic from this article".
  8. On the first run it will ask for preferences (EXTEND.md): default layout/style, aspect ratio, language, image backend. To change them later, just say "reconfigure baoyu-infographic preferences".
View source on GitHub ↗License: MIT