AugmentClaude

LJG Card

Transform content into styled PNG cards with seven layout templates.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/ljg-card-lijigang/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Content caster (铸). Transforms content into PNG visuals. Seven molds: -l (default) long reading card, -i infograph, -m multi-card reading cards (1080x1440), -v editorial sketchnote (problem→failure→pivot→insight→naming, magazine + archive layout), -c comic (manga-style B&W), -w whiteboard (marker-style board layout), -b big-fonts attachment card (1080x1440, weathered 碑刻 style for 小红书). Output to ~/Downloads/. Use when user says '铸', 'cast', '做成图', '做成卡片', '做成信息图', '做成海报', '视觉笔记', 'sketchnote', '杂志', 'editorial', '漫画', 'comic', 'manga', '白板', 'whiteboard', '大字', '附件图', 'big fonts', '小红书卡片'. Replaces ljg-cards and ljg-infograph.

What this skill does

ljg-card: 铸

内容进去,PNG 出来。模具决定形状。

参数

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)

约束

输出是视觉文件(PNG),L0 里的 Org-mode、Denote、ASCII-only 规范不适用。

通用规矩

获取内容

  • URL:WebFetch 抓
  • 粘贴文本:直接用
  • 文件路径:Read 读

文件命名

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)。

截图工具

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

Footer

  • 左侧:logo + 李继刚(模板已硬编码)
  • 右侧:内容来源,可选。有明确来源(作者名、arxiv ID、网站名)就填 {{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)。

交付

报告文件路径。

品味准则

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。

执行

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
-lreferences/mode-long.mdassets/long_template.html
-ireferences/mode-infograph.mdassets/infograph_template.html
-mreferences/mode-poster.mdassets/poster_template.html
-vreferences/mode-sketchnote.mdassets/sketchnote_template.html
-creferences/mode-comic.mdassets/comic_template.html
-wreferences/mode-whiteboard.mdassets/whiteboard_template.html
-breferences/mode-big.mdassets/big_template.html

Related skills