ljg-card

Original：🇨🇳 Chinese

Translated

1 scriptsChecked / no sensitive code detected

Content Caster (Zhù). Converts content into PNG visual assets. Five molds available: -l (default) long reading card, -i infograph, -m multi-card reading cards (1080x1440), -v visual sketchnote, -c comic (manga-style black & white). Outputs to ~/Downloads/. Activate when the user uses terms like '铸', 'cast', '做成图', '做成卡片', '做成信息图', '做成海报', '视觉笔记', 'sketchnote', '漫画', 'comic', 'manga'. Replaces ljg-cards and ljg-infograph.

2installs

Sourcelijigang/ljg-skills

Added on2026-03-23

NPX Install

npx skill4agent add lijigang/ljg-skills ljg-card

SKILL.md Content (Chinese)

View Translation Comparison →

ljg-card: Zhù

Cast content into visible formats. Input content, output PNG. The mold determines the format.

Parameters

Parameter	Mold	Dimensions	Description
`-l` (default)	Long Card	1080 x auto	Single reading card, content automatically adjusts height
`-i`	Infograph	1080 x auto	Content-driven adaptive visual layout
`-m`	Multi-card	1080 x 1440	Automatically splits into multiple reading cards
`-v`	Visual Sketchnote	1080 x auto	Hand-drawn style sketchnote, dynamically selects style routes
`-c`	Comic	1080 x auto	Japanese-style black & white comic, dynamically selects manga artist visual language

Constraints

This skill outputs visual files (PNG) and does not comply with the Org-mode, Denote, and ASCII-only specifications in L0.

Shared Foundations

Content Retrieval

URL --> Retrieve via WebFetch
Pasted text --> Use directly
File path --> Retrieve via Read

File Naming

Extract the title or core idea from the content as

{name}

(use Chinese directly, remove punctuation, ≤20 characters).

Screenshot Tool

bash

node ~/.claude/skills/ljg-card/assets/capture.js <html> <png> <width> <height> [fullpage]

Dependency: playwright in

~/.claude/skills/ljg-card/node_modules/

. If errors occur:

bash

cd ~/.claude/skills/ljg-card && npm install playwright && npx playwright install chromium

arxiv Detection

When the content source is an arxiv paper (URL contains

arxiv.org

, filename includes the

paper

tag, or arxiv ID appears in the content), extract the arxiv ID (format

XXXX.XXXXX

) and display it on the right side of the card footer. Applicable to

-l

and

-i

molds (not applicable to

-m

multi-card as it has no footer).

Delivery

Report the file path

Taste Guidelines

Shared by all molds. Before executing any mold, read

references/taste.md

to maintain this baseline of visual quality throughout the process.

Core principle: Avoid AI-generated traces — prohibit Inter font, pure black, tri-sectioned cards, centered Hero sections, AI-style copy, and fake data.

Execution

Select the mold based on parameters, read

references/taste.md

+ the corresponding mode file, and follow the steps to execute:

-l (default): Long Card

Read

references/mode-long.md

and follow its steps.

Template:

assets/long_template.html

-i: Infograph

Read

references/mode-infograph.md

and follow its steps.

Template:

assets/infograph_template.html

-m: Multi-card

Read

references/mode-poster.md

and follow its steps.

Template:

assets/poster_template.html

-v: Visual Sketchnote

Read

references/mode-sketchnote.md

and follow its steps.

Template:

assets/sketchnote_template.html

-c: Comic

Read

references/mode-comic.md

and follow its steps.

Template:

assets/comic_template.html

ljg-card

NPX Install

Tags

SKILL.md Content (Chinese)

ljg-card: Zhù

Parameters

Constraints

Shared Foundations

Content Retrieval

File Naming

Screenshot Tool

arxiv Detection

Delivery

Taste Guidelines

Execution

-l (default): Long Card

-i: Infograph

-m: Multi-card

-v: Visual Sketchnote

-c: Comic