baoyu-infographic
Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".
npx skills add JimLiu/baoyu-skills --skill baoyu-infographic --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Generates professional infographics by analyzing content and recommending a combination of a layout and a visual style from 21 layouts and 22 styles. It produces publication-ready infographics and supports prompts when users request terms like infographic, 信息图, visual summary, 可视化, or 高密度信息大图.
How it works
- User input tools: prompts the user for input using built-in UI tools when available, or asks via a numbered plain-text message otherwise. It supports batching multiple questions if the runtime allows.
- Image generation: The skill outlines a prioritization for choosing an image backend and specifies rules for raster backends and backends like imagegen, codex-imagegen, or Cursor GenerateImage; it requires the prompt file to be written to prompts/ before invoking any backend. It prohibits using SVG or other code-based rendering as a substitute when raster backends are unavailable.
- Output structure: It defines an output structure with a topic slug under infographic/ and includes source, analysis, structured-content, prompts, and the final PNG.
- Reference images: It accepts reference images for style, palette, or composition, and uses them via direct file paths or prompt trait extraction depending on backend support.
- Confirmation policy: It defaults to asking for confirmation before generation, unless explicitly overridden with a --no-confirm style flag.
When to use it
Use when the user asks to create an infographic, 信息图, visual summary, 可视化, or 高密度信息大图.
What it can touch
- Tools: built-in user-input tools (e.g., AskUserQuestion, request_user_input, clarify, ask_user).
- Image backends: imagegen-like backends or Cursor GenerateImage, with explicit backing rules and prompt-file requirements under prompts/.
- Output paths: infographic/{topic-slug}/ with files including source-{slug}, analysis.md, structured-content.md, prompts/infographic.md, and infographic.png.
Caveats
- Requires confirmation before generation unless explicitly skipped with a flag.
- Raster image backend must be resolved from the specified priority chain; SVG or other code-based rendering is prohibited as a substitute.
- Text in generated infographics should not be altered by programmatic overlays; if text is incorrect, regenerate from corrected prompt.
- Prompts must be written to prompts/ before backend invocation for reproducibility.
# Infographic Generator Two dimensions: **layout** (information structure) × **style** (visual aesthetics). Freely combine any layout with any style. ## User Input Tools When this skill prompts the user, follow this tool-selection rule (priority order): 1. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent. 2. **Fallback**: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question. 3. **Batching**: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order. Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes. ## Image Generation Tools When this skill needs to render an image, resolve the backend in this order: 1. **Current-request override** — if the user names a specific backend in the current message, use it. 2. **Saved preference** — if `EXTEND.md` sets `preferred_image_backend` to a backend available right now, use it. 3. **Auto-
- User Input Tools
- Image Generation Tools
- Reference Images
- Confirmation Policy
- Options
- Layout Gallery (21)
- Style Gallery (22)
- Recommended Combinations
- Keyword Shortcuts
- Output Structure
- Core Principles
- Workflow
- Step 1: Setup & Analyze
- Step 2: Generate Structured Content → structured-content.md
What does the baoyu-infographic skill do?
Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".
How do I install it?
Run `npx skills add JimLiu/baoyu-skills --skill baoyu-infographic --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From JimLiu/baoyu-skills, a repository with 24,562 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.