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 judeyang/judeyang-skills --skill tujinpdfgit clone --depth 1 https://github.com/judeyang/judeyang-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/judeyang/judeyang-skills/tujinpdf)<a href="https://agentmods.dev/skills/judeyang/judeyang-skills/tujinpdf"><img src="https://agentmods.dev/badge/skills/judeyang/judeyang-skills/tujinpdf/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/judeyang/judeyang-skills/tujinpdf"><img src="https://agentmods.dev/badge/skills/judeyang/judeyang-skills/tujinpdf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00072 | $0.02878 |
| Opus 5 | $0.00036 | $0.01439 |
| Sonnet 5 | $0.00014 | $0.00576 |
| Haiku 4.5 | $0.00007 | $0.00288 |
Grade A, and why
tujinpdf 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 12d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
土金杂志风PDF
Created by JudeYang.
把任意文档改成土金色系杂志风 PDF。这个 skill 只做三件事：
- 读取用户给的内容。
- 重新排版成土金色系 A4 HTML。
- 用浏览器渲染成 PDF。
不要承担内容编辑、内容筛选、内容判断、事实修正、口径调整。除非用户明确要求，否则不要改原文。
Operating Contract
每次触发后，先判断当前任务属于哪一类：
- 新建排版：用户给内容，需要生成新的 HTML + PDF。
- 续改旧版：用户给已有 HTML/PDF，需要在原 HTML 上改版。
- 样式修复：用户指出溢出、重叠、分页、表格或封面问题，只修版式。
- 内容编辑 + 排版：用户明确要求润色、精简、改口径或重写内容；先把内容编辑范围说清楚，再排版。
默认只做新建排版或续改旧版。任务不清楚时，按“只改呈现，不改内容”处理，并在回复里说明这个边界。
同时判断文档类型，用它决定版式重点，而不是改变内容：
客户确认归档：突出确认结论、资产图片、签收/确认区域、版本信息。项目复盘报告：突出时间线、调整记录、影响范围、最终结果。提案型PDF：突出问题、方案、价值、执行路径和下一步。资产设定集：突出角色/场景/产品/道具图片、名称、用途和状态。分镜脚本归档：突出镜号、画面、台词/旁白、资产引用和确认状态。普通文档美化：只做章节、表格、封面和可读性优化。
文档类型只控制排版模板和 QA 重点，不授权修改事实、删减内容或合并版本。
Input
支持任意可读取内容：
- Markdown / TXT
- HTML
- PDF / DOCX / XLSX 中提取出来的文本或表格
- 项目总结、报告、方案、报价单、记录、归档材料
- 用户直接贴在对话里的内容
Output
默认输出：
- 一个
.html源文件 - 一个同名
.pdf - 必要时一个预览截图用于检查
HTML 必须保留，因为后续改版要直接在原 HTML 上升级，不要每次新建一版。
文件命名：
- 新建：
文档主题_土金PDF_v01.html、文档主题_土金PDF_v01.pdf - 续改：沿用原主题并递增版本号，如
项目总结_土金PDF_v02.html - 截图：
文档主题_土金PDF_v01_preview.png - 不覆盖旧版本；如果用户明确要求覆盖，先进入 checkpoint。
输出目录优先使用用户指定目录；没有指定时，放在当前任务的 outputs/ 或项目约定交付目录。
Core Workflow
- 读取输入：确认源文件路径、文本内容、目标读者、是否需要保留全部内容。
- 提取结构：识别标题、日期、元信息、章节、表格、列表、关键数字和附件说明。
- 生成 HTML：使用 A4 页面、土金色系变量、封面、页眉页脚、章节和表格样式。
- 渲染 PDF：运行
scripts/render-html-pdf.js输出 PDF 和预览截图。 - 质量检查：检查 PDF 可打开、页数合理、文本可提取、截图无明显溢出重叠。
- 交付说明：说明生成了哪些文件、是否改动原文、未验证项和下一步可改什么。
Style
目标风格：土金色系、克制、杂志感、留白充足、中文精致排版。
可选主题锁：
经典土金：默认主题，适合确认归档、项目总结、正式报告。深棕高级：适合品牌片、提案、客户正式交付。米纸杂志：适合设定集、人文内容、视觉资产归档。黑金档案：适合重要复盘、阶段总结、强对比封面。
如果用户没有指定，默认使用 经典土金。不要接受任意 hex 值拼色；如果用户要求改色，先映射到上述主题之一或明确说明会偏离土金PDF风格锁。
基础视觉参数：
- 页面：A4，
210mm x 297mm - 背景：暖纸色
#f4ede1 - 辅助底色：
#efe6d6 - 主文字：
#1f1a16 - 次文字：
#4a3f33 - 注释文字：
#8a7a68 - 金色线条/强调：
#a8854a - 细线：
rgba(31,26,22,0.10~0.18)
排版规则：
- 首页做封面：品牌/来源、文档类型、主标题、关键元信息。
- 正文使用章节结构：章号、标题、正文、表格、卡片。
- 章节之间留足呼吸感，不要堆满。
- 标题居中或左对齐要根据页面结构决定，不要混乱。
- 表格：短内容居中，长内容左对齐。
- 表格表头必须统一居中。不要为了让正文长内容左对齐，把左对齐类或样式加到
th上。正确做法是：th { text-align: center; }，正文短内容单元格居中，正文长内容单元格左对齐。 - 不要卡片套卡片。
- 不要额外添加无意义装饰图、雷达图、六边形图、占位标签或引文。
- 只有当源文档本来有图表/引用/关键数字时，才把它们设计成可视元素。
What ships with it
17 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.
- .gitignore 30 B
- agents/openai.yaml 262 B
- assets/banner.svg 2.4 KB
- assets/hero.gif 110 KB
- assets/quality-gate.svg 1.8 KB
- assets/workflow.svg 1.8 KB
- examples/expected-output-notes.md 429 B
- examples/sample-report.md 756 B
- LICENSE 1.0 KB
- package.json 23 B
- README_EN.md 5.8 KB
- README.md 5.2 KB
- references/fatepaw-style-notes.md 1.4 KB
- scripts/render-html-pdf.js 4.1 KB runs code
- scripts/validate-output.mjs 1.9 KB runs code
- templates/base-a4.html 4.2 KB
- test-prompts.json 761 B
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.
- 12d ago First seen · 222 lines · 72 tokens per session scan A 444b4129187a
tujinpdf is a skill published in the GitHub repository judeyang/judeyang-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 2,878 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.