搜索与研究
infographize
Convert markdown documents into AntV infographic SVGs. Analyzes content structure, selects optimal template, generates AntV syntax, and renders to SVG. Use when user wants to create infographics, visual summaries, or storytelling visuals from markdown.
digital-stoic-org · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add digital-stoic-org/agent-skills --skill infographize技能说明
name: infographize description: Convert markdown documents into AntV infographic SVGs. Analyzes content structure, selects optimal template, generates AntV syntax, and renders to SVG. Use when user wants to create infographics, visual summaries, or storytelling visuals from markdown. tools: Bash, Read, Write model: sonnet
Infographize
Convert any markdown document into a visual infographic SVG via AntV Infographic SSR.
Workflow
- Dependency check: Run
bun run -e "import '@antv/infographic'" 2>/dev/null. If it fails, install viainstall-dependencyskill (@antv/infographic, bun package) before proceeding - Read the source markdown file
- Read
<skill_dir>/reference.mdfor template catalog and data field mappings - Analyze content structure — identify the dominant information type:
- Bullet lists, features, options →
list-* - Numbered steps, processes, timelines →
sequence-* - Pros/cons, A vs B, SWOT →
compare-* - Nested structure, org chart, taxonomy →
hierarchy-* - Connected items, network, dependencies →
relation-* - Numeric data, percentages, stats →
chart-*
- Bullet lists, features, options →
- Select the best template from the catalog (match content pattern to template's "best for")
- Map markdown content → AntV syntax using the correct data fields for that category
- Write the AntV syntax to a
.txtfile next to the output path - Render by calling:
bun run <skill_dir>/scripts/render.ts <syntax-file> <output.svg> --preview
Output
- Default output: same directory as input, same basename with
.svgextension - User can specify a custom output path as second argument
Content Mapping Rules
- Be concise: Infographics are visual-first. Distill prose into short labels (3-7 words) and brief descriptions (1 sentence max)
- 60/40 rule: Favor graphics over text. Cut detail that doesn't serve the visual narrative
- One idea per infographic: If the markdown covers multiple distinct topics, pick the primary one or ask the user
- Preserve hierarchy: Map heading levels to visual hierarchy (title → section → item)
- Extract data: Pull numbers, percentages, counts into
valuefields when available
Theme
Default: light. User can request dark, hand-drawn, or custom colors — see reference.md for themeConfig options.