ljg-skills is a collection of custom Codex skills for tasks such as learning, writing, reading, relationship analysis, image creation, and investment analysis. Codex users install selected skills or the whole collection through a skills command-line interface. The catalogue entries are the collection's individual skills, plugin, and instruction.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lijigang/ljg-skills --skill ljg-cardgit clone --depth 1 https://github.com/lijigang/ljg-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lijigang/ljg-skills/ljg-card)<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-card"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-card/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-card"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-card.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.03887 |
| Opus 5 | $0.00054 | $0.01944 |
| Sonnet 5 | $0.00022 | $0.00777 |
| Haiku 4.5 | $0.00011 | $0.00389 |
Grade A, and why
ljg-card scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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。
参数
| 参数 | 模具 | 尺寸 | 图像角色 |
|---|---|---|---|
-l(默认) |
长图 · 静线叙事 | 1080 × auto | 1 个安静主场景;必要时追加至多 2 个连续视觉拍点 |
-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 |
-c |
漫画 | 1080 × auto | 缺口驱动、同案重跑的漫画分镜 |
-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 |
未给参数时使用 -l。
必读顺序
-l、-c、-w 每次执行都必须依次 Read:
references/taste.mdreferences/image-generation.md- 当前 mode 文件
- 当前 HTML 模板
不得跳过共享图像协议直接写提示词,也不得把一种 mode 的图像语法套给另一种。
-f 依次 Read:
references/taste.mdreferences/mode-full.mdassets/full_template.html
-f 不生成新图;只有原稿自带图片时才补读 references/image-generation.md 的资产身份、来源保真与本地落盘合同。
-f 字体优先级
-f 的所有编辑性文字优先使用本机已安装的 KingHwa_OldSong,包括 title、headline、章节标题、正文、强调、图注、表头与署名,从而保持整张长卡的字体气质统一。浏览器检测不到时,正文回退到 Songti SC、STSong、Noto Serif CJK SC 与 serif,标题类文字回退到 PingFang SC、Hiragino Sans GB、Microsoft YaHei 与系统 sans。不得为了制卡联网下载、临时安装或远程引用该字体。code、pre 与来源行保留等宽字体,因为字符对齐在这些位置承担语义。
-f 长文阅读面
-f 通常产生超长卡片,因此使用独立于 -l 的白底黑字阅读面:画布固定为纯白 #FFFFFF,普通正文使用深中性黑 #171717,辅助信息只用克制的中性灰。1080px 成品的普通正文不小于 40px,行高保持 1.9,正文有效宽度约 896px;段距默认 36px,章节间距明显大于段落间距。列表与引用同为 40px/1.9,表格 34px,脚注与代码块 32px,图注 30px。以约 390px 手机显示宽度复查,正文约等效 14.4px;允许长图增高,不为压缩高度缩字。不得把暖纸底、小号网页正文、过紧行距或大面积彩色模块带入 -f。
全局临时目录约束
无论从哪个目录启动,制卡前都必须在 /tmp 下建立本任务独占的临时目录。生成图候选稿、用于组版的源图、HTML、CSS、矢量草稿、渲染输入、截图草稿、QA 切片、缓存与日志等所有中间产物,全部只能写入该目录。
只有用户明确要求交付的最终文件可以写入 /tmp 之外。候选 PNG 和未通过验收的渲染结果仍属于中间产物。完成前检查当前目录和仓库没有遗留中间文件,最终交付物验收后清理本任务的临时目录。
共同生产线
- 读取 URL、粘贴文本或本地文件,确认标题、作者、来源与事实边界。
-f锁定来源、建立有序原文块账本,直接进入references/mode-full.md;不经过提炼、视觉母题或图片生成。-l、-c提炼内容判断,建立视觉母题表:判断 → 冲突 → 视觉动词 → 承载物 → 安全区。-w先把此次输入保存为精确来源快照,再运行assets/prepare-whiteboard-source.ts建立逐段来源清单;必须让论证账本覆盖这份独立清单,才可决定哪些承重步骤需要视觉化。不能从一句摘要直接进入版式。-w的生成图预算为 0–4 幅。-l、-c调用当前环境的 image generation 工具,先生成一张代表图校准语义与系列风格;-w的资产预算大于 0 时才做同样校准,0 幅是合法结果。- 将图片保存为本地 PNG/JPG,逐一核对文件、尺寸、构图、无字与来源属性。
- 将所有可读文字、数字、公式、标签、箭头和来源放入 HTML/CSS;图片只承担场景与隐喻。
- 读取对应模板,替换全部占位符。
-l、-c的顶部图槽无图时必须显式设为data-state="empty";有图时必须提供本地路径和语义化alt。-w没有顶部图槽:把最终论证账本写入{{LOGIC_LEDGER_JSON}},每幅生成图只在对应步骤内部出现,并用data-source-claim回指该步骤 ID。 - 截图前等待字体与全部图片加载成功;任一图片损坏就停止。
- 交付前检查整图;长图再用重叠切片覆盖全部高度。
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/audit.ts 17 KB runs code
- assets/build-fixtures.ts 39 KB runs code
- assets/capture.test.ts 8.6 KB runs code
- assets/capture.ts 30 KB runs code
- assets/comic_template.html 2.2 KB
- assets/full_template.html 6.2 KB
- assets/logo.png 319 KB
- assets/long_template.html 7.3 KB
- assets/prepare-whiteboard-source.test.ts 1.4 KB runs code
- assets/prepare-whiteboard-source.ts 2.1 KB runs code
- assets/verify-full-text.test.ts 3.8 KB runs code
- assets/verify-full-text.ts 6.4 KB runs code
- assets/whiteboard_template.html 11 KB
- bun.lock 775 B
- package-lock.json 1.6 KB
- package.json 190 B
- references/image-generation.md 6.5 KB
- references/mode-comic.md 8.7 KB
- references/mode-full.md 8.3 KB
- references/mode-long.md 6.8 KB
- references/mode-whiteboard.md 13 KB
- references/taste.md 2.7 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed 17b59418eee0
- 13d ago First seen · 189 lines · 108 tokens per session scan A 1d27c40ef7db
ljg-card is a skill published in the GitHub repository lijigang/ljg-skills (7,340 stars, last pushed 4d ago), licensed MIT. It adds 108 tokens to every session and 3,887 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…