AI Skills
ljg-card

ljg-card

Popular

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.

6.5Kstars
764forks
Updated 7/14/2026
Get SkillSource Code

Related Skills

prospecting36Kagent-browser36Kopencli-autofix26K
SKILL.md
readonlyread-only
name
ljg-card
description

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.

version
3.0.0

ljg-card: 铸

Content in, PNG out. The mold determines the shape.

Parameters

Flag Mold Dimensions Description
-l (default) Long image 1080 x auto Single reading card, height auto-expands
-i Infograph 1080 x auto Layout follows content, no fixed template
-m Multi-card 1080 x 1440 Auto-splits into multiple reading cards
-v Sketchnote 1080 x auto Magazine-style concept narrative: problem→failure→pivot→insight→naming
-c Comic 1080 x auto Japanese-style B&W manga, artist chosen by content tone
-w Whiteboard 1080 x auto Handwritten reasoning chain on washi paper, arrows connecting concepts
-b Big fonts 1080 x 1440 Stele-carved large characters + washi + drop shadow, for 小红书 attachments (single sentence/short paragraph)

Constraints

Output is a visual file (PNG). L0 Org-mode, Denote, and ASCII-only conventions do not apply.

General Rules

Getting Content

  • URL: Fetch via WebFetch
  • Pasted text: Use directly
  • File path: Read via Read

File Naming

Extract title or core idea from content as {name} (use Chinese directly, remove punctuation, ≤ 20 characters).

Screenshot Tool

node assets/capture.js <html> <png> <width> <height> [fullpage]

Run from skill root directory, depends on playwright in root node_modules/. On error:

npm install playwright && npx playwright install chromium

Footer

  • Left: logo + 李继刚 (hardcoded in template)
  • Right: content source, optional. If there is a clear source (author name, arxiv ID, site name), fill {{SOURCE_LINE}}: <span class="info-source">来源文字</span>; otherwise leave empty string. Applies to -l, -i, -v, -c, -w (-m multi-card has no footer).

Delivery

Report the file path.

Taste Guidelines

Regardless of mold, first Read references/taste.md. Common visual baseline for all molds: no Inter font, no pure black, no three-column cards, no AI copywriting tone, no fake data.

Execution

Select mold by parameter, Read references/taste.md + corresponding mode file, follow steps:

Flag Mode file Template
-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