LJG Content Caster Agent Skill

Transforms text and web content into high-quality visual PNGs using specialized design templates and artistic styles.

Context cost
27.4k tokensestimated from the bundle, loaded when it triggers
Bundle
22 of 23 fileshanded out here; the rest is at its source
Licence
MITthe author’s own terms
Last change
—v7.4.2
Servers it uses
Noneruns standalone

What it does

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'.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

design
Filed under

Design & Media

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md16.2 kB · preview
--- name: ljg-card user_invocable: true version: "7.4.2" ---
8# ljg-card:铸
9
10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。
11
12-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。
13
14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。
15
16## 参数
17
18| 参数 | 模具 | 尺寸 | 图像角色 |
19|---|---|---|---|
20| -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 |
21| -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 |
22| -c | 漫画 | 1080 × auto | 缺口驱动、同案重跑的漫画分镜 |
23| -w | 白板 · 纵向论证 | 1080 × auto | 嵌入承重推理节点的局部手绘动作;不设顶部主视觉 |
24
25未给参数时使用 -l。
26
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md604 words
Files22
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈100
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
27,325
on trigger
The instruction body and 21 supporting files, read only when the skill fires.
13.7%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

27.4k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

The download carries 22 of the 23 files in its source folder; the list here names 22 files, 225.2 kB on disk. Mostly text — the instructions the model reads — with 8 scripts in it that your client would run only if the instructions tell it to. The other one is not in the download, nor is 1 file of a type a skill download does not carry — listed after these, with why.

  • SKILL.md16.2 kB
  • package-lock.json1.6 kB
  • package.json0.2 kB
  • assets/audit.ts16.9 kB
  • assets/build-fixtures.ts44.9 kB
  • assets/capture.test.ts9.4 kB
  • assets/capture.ts30.2 kB
  • assets/comic_template.html2.3 kB
  • assets/full_template.html6.3 kB
  • assets/long_template.html7.9 kB
  • assets/prepare-whiteboard-source.test.ts1.5 kB
  • assets/prepare-whiteboard-source.ts2.2 kB
  • assets/verify-full-text.test.ts3.9 kB
  • assets/verify-full-text.ts6.5 kB
  • assets/whiteboard_template.html11.8 kB
  • references/image-generation.md7.2 kB
  • references/learning-design.md9.9 kB
  • references/mode-comic.md8.9 kB
  • references/mode-full.md8.5 kB
  • references/mode-long.md9.7 kB
  • references/mode-whiteboard.md15.9 kB
  • references/taste.md3.3 kB

Not in the download

Not carried is a type a skill download does not hold. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take them from its source.

  • assets/logo.pngread · not carried
  • bun.locknot carried
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 8 scripts beside the text, so the download is 22 files — not the whole of its source: 2 files are left out, and the skill reads one of them. They are listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# LJG Content Caster · 27.4k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/ljg-content-caster/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/ljg-content-caster" ] && { [ ! -e .claude/skills/ljg-content-caster ] || { mv .claude/skills/ljg-content-caster "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/ljg-content-caster" .claude/skills/ && echo "Installed .claude/skills/ljg-content-caster"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add lijigang/ljg-content-caster

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/ljg-content-caster/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/ljg-content-caster/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/ljg-content-caster" ] && { [ ! -e ~/.claude/skills/ljg-content-caster ] || { mv ~/.claude/skills/ljg-content-caster "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/ljg-content-caster" ~/.claude/skills/ && echo "Installed ~/.claude/skills/ljg-content-caster" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/ljg-content-caster/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as ljg-card in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, ljg-content-caster. Not in this download: 2 files of its source, 1 of them read by its SKILL.md or scripts (the full list, and why). Take them from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version7.4.2
Publishedno release date on file
PriceFree
Referencelijigang/ljg-content-caster

Versions

v7.4.2 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v7.4.2
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v7.4.2 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill