Individual skill

ljg-card

Content caster (铸). Transforms text into PNG through precise HTML typography and, when the mold needs it, generated raster imagery. Four molds: -l (default) long reading card, -f source-faithful full text, -c comic, -w whiteboard. USE WHEN user says '铸', 'cast', '做成图', '做成卡片', '做成海报', '原文排版', '全文卡片', '漫画', or '白板'.

skills/ljg-card/SKILL.md

Read pinned source

Source commit 76b5fb9b657f420287a421737a3a9778c9e53379

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 7,731
Repository last updated: Nov 2, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

design Derived category
writing Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 16,210 bytes
SKILL.mdcore · 16,210 bytes
SKILL.mdcore · 16,210 bytes
SKILL.mdcore · 16,210 bytes
SKILL.mdcore · 16,210 bytes
assets/audit.tsruns · 16,934 bytes
assets/build-fixtures.tsruns · 44,916 bytes
assets/capture.test.tsruns · 9,393 bytes
assets/capture.tsruns · 30,187 bytes
assets/comic_template.htmlasset · 2,296 bytes
assets/full_template.htmlasset · 6,315 bytes
assets/logo.pngasset · 326,462 bytes
assets/long_template.htmlasset · 7,940 bytes
assets/prepare-whiteboard-source.test.tsruns · 1,454 bytes
assets/prepare-whiteboard-source.tsruns · 2,175 bytes
assets/verify-full-text.test.tsruns · 3,926 bytes
assets/verify-full-text.tsruns · 6,505 bytes
assets/whiteboard_template.htmlasset · 11,759 bytes
bun.lockasset · 775 bytes
package-lock.jsonasset · 1,592 bytes
package.jsonruns · 190 bytes
references/image-generation.mddoc · 7,239 bytes
references/learning-design.mddoc · 9,859 bytes
references/mode-comic.mddoc · 8,918 bytes
references/mode-full.mddoc · 8,497 bytes
references/mode-long.mddoc · 9,725 bytes
references/mode-whiteboard.mddoc · 15,894 bytes
references/taste.mddoc · 3,304 bytes

Read excerpt


# ljg-card：铸

内容进去，PNG 出来。生成图负责把思想变成可见动作，HTML 负责把话说准确；`-f` 只设计原文的呈现，不改动原文，也不生成新图。

`-l`、`-w` 承担知识讲解时，还要接通「具体情形 → 判别依据 → 有条件的关系 → 具体结果」。读者应能从正文里的动作或状态看出对象凭什么属于某个概念，再用关系推出眼前的结果；只把例子放在术语旁边，连接仍然缺失。先确定目标读者要完成什么判断，再决定材料和画面；下上结构不规定版面上下，也不要求每张卡从故事开头。文学、叙事与审美表达按自身目的组织，不强加习题。

成品在内容自身的结论、问题或余韵处结束，之后只留署名与来源。不要追加「阅读边界」、免责声明、制作说明或验收说明，也不要换个标题保留这类尾注。会改变理解的原文条件、分歧与限制，就近融入相应论证；提炼范围、材料缺口和验证状态放在交付回复中。`-f` 原稿已有的段落仍按全文保真合同保留。

## 参数

| 参数 | 模具 | 尺寸 | 图像角色 |
|---|---|---|---|
| `-l`（默认） | 长图 · 静线叙事 | 1080 × auto | 0–3 幅；有理解增益时用 1 个安静主场景，必要时追加连续视觉拍点 |
| `-f` | 全文 · 原文排版 | 1080 × auto | 生成图固定为 0；只保真呈现原稿自带图片 |