Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From ljg-skills
Transforms content into PNG visuals with seven layout molds: long reading card, infograph, multi-card, sketchnote, comic, whiteboard, and big-fonts card. Outputs to ~/Downloads/.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ljg-skills:ljg-cardThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
内容进去，PNG 出来。模具决定形状。
assets/big_template.htmlassets/capture.jsassets/comic_template.htmlassets/infograph_template.htmlassets/logo.pngassets/long_template.htmlassets/poster_template.htmlassets/sketchnote_template.htmlassets/whiteboard_template.htmlbun.lockpackage-lock.jsonpackage.jsonreferences/mode-big.mdreferences/mode-comic.mdreferences/mode-infograph.mdreferences/mode-long.mdreferences/mode-poster.mdreferences/mode-sketchnote.mdreferences/mode-whiteboard.mdreferences/taste.md内容进去，PNG 出来。模具决定形状。
| 参数 | 模具 | 尺寸 | 说明 |
|---|---|---|---|
-l（默认） | 长图 | 1080 x auto | 单张阅读卡，内容自动撑高 |
-i | 信息图 | 1080 x auto | 布局跟着内容长，没有固定版式 |
-m | 多卡 | 1080 x 1440 | 自动切成多张阅读卡片 |
-v | 视觉笔记 | 1080 x auto | 像杂志专题讲一个概念：问题→失败→转折→顿悟→命名 |
-c | 漫画 | 1080 x auto | 日式黑白漫画，按内容气质选漫画家 |
-w | 白板 | 1080 x auto | 和紙底手写推理链，箭头串概念 |
-b | 大字 | 1080 x 1440 | 碑刻大字 + 和紙 + 外阴影，小红书附件用（单句/短段） |
输出是视觉文件（PNG），L0 里的 Org-mode、Denote、ASCII-only 规范不适用。
从内容提取标题或核心思想作 {name}（中文直接用，去标点，≤ 20 字符）。
node assets/capture.js <html> <png> <width> <height> [fullpage]
从 skill 根目录运行，依赖根目录 node_modules/ 里的 playwright。报错时：
npm install playwright && npx playwright install chromium
{{SOURCE_LINE}}：<span class="info-source">来源文字</span>；没有就留空字符串。适用于 -l、-i、-v、-c、-w（-m 多卡无 footer）。报告文件路径。
不管走哪个模具，先 Read references/taste.md，全部模具共用的视觉底线：禁 Inter 字体、禁纯黑、禁三等分卡片、禁 AI 文案腔、禁假数据。
按参数选模具，Read references/taste.md + 对应 mode 文件，照步骤走：
| 参数 | mode 文件 | 模板 |
|---|---|---|
-l | references/mode-long.md | assets/long_template.html |
-i | references/mode-infograph.md | assets/infograph_template.html |
-m | references/mode-poster.md | assets/poster_template.html |
-v | references/mode-sketchnote.md | assets/sketchnote_template.html |
-c | references/mode-comic.md | assets/comic_template.html |
-w | references/mode-whiteboard.md | assets/whiteboard_template.html |
-b | references/mode-big.md | assets/big_template.html |
2plugins reuse this skill
First indexed Jul 2, 2026
npx claudepluginhub vegayan2024/ljg-skillsTransforms content into PNG visuals with seven layout molds: long reading card, infograph, multi-card, sketchnote, comic, whiteboard, and big-fonts card. Outputs to ~/Downloads/.
Generates social media infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Splits content into 1-10 cartoon-style cards for platforms like Xiaohongshu and WeChat.
Generates social media infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style cards for platforms like Xiaohongshu and WeChat.