Layout-Preserving PDF Translation Agent Skill

Translates PDF papers and documents while preserving original formatting, formulas, tables, and flowchart text using LLM engines.

Context cost
2.7k tokensestimated from the bundle, loaded when it triggers
Bundle
4 files · 17.7 kB1 script among them — read before you run
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

保留排版地翻译 PDF 文献(默认英→中):直接解析 PDF,按版面结构逐块提取文字,送 LLM (默认 DeepSeek)翻译后按原坐标回填,保留文字颜色/样式,连表格、流程图/图内文字也翻译, 公式 / 图片整块原样保留;先自动抽取术语表保证缩写一致、不胡乱展开(如 MI 按上下文判为 密歇根州而非心肌梗死)。输出纯译文版(.mono.pdf)、中英对照版(.dual.pdf)和术语表 (.glossary.csv)。底层默认 BabelDOC 引擎,可回退 pdf2zh。当用户说「翻译这个 PDF」 「把这篇论文/文献翻译成中文」「PDF 翻译保留排版」「翻译英文文献」「translate this pdf」 「translate this paper to Chinese」时触发。需要本机 DeepSeek key(交互式 zsh 的 DEEPSEEK_API_KEY,脚本自动取)。

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.

productivitytranslation

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.md5.4 kB · preview
--- name: pdf-translate ---
14# PDF 文献翻译(保留排版 · 翻表格/流程图 · 术语一致)
15
16直接解析 PDF → DocLayout 版面分析 → **自动抽取全文术语表**(缩写按上下文判定)→ 逐块翻译
17(保留文字颜色/样式,表格单元格、流程图框内文字一并翻)→ 按原坐标回填,公式/图片原样保留。
18输出三份:纯译文 *.mono.pdf、中英对照 *.dual.pdf(默认**交替页**:一页原文、一页译文,适合打印;
19加 --side-by-side 改回左右并排同页)、术语表 *.glossary.csv。
20
21底层默认 **[BabelDOC](https://github.com/funstory-ai/BabelDOC)** 引擎(命令 babeldoc,
22中间表示重排,比 pdf2zh 原版在颜色/表格/流程图/版面重叠上都更好),翻译后端 **DeepSeek**
23(OpenAI 兼容)。可用 --engine pdf2zh 回退到原版 pdf2zh。
24
25> 为什么不是原版 pdf2zh:原版会把文字**颜色重置为黑**、把**表格/流程图当 figure 整块跳过**、
26> 中文比英文长时**行重叠**、且逐块翻译**无上下文**导致缩写乱译。BabelDOC 逐一解决了这些。
27
28## 用法
29
30都走 scripts/pdf-translate.sh(自动取 DeepSeek key、建输出目录、设好上面那套默认值):
31
32```bash
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md347 words
Files4
Licencenot declared
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.

≈120
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
2,580
on trigger
The instruction body and 3 supporting files, read only when the skill fires.
1.4%
of a 200k window
Ten skills this size would take about 14% of the window before you open a file.
050k100k150k200k context window

2.7k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

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

4 files, 17.7 kB on disk. Mostly text — the instructions the model reads — with 1 script in it that your client would run only if the instructions tell it to.

  • SKILL.md5.4 kB
  • README.md5.2 kB
  • scripts/config.example.json0.2 kB
  • scripts/pdf-translate.sh6.9 kB
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 1 script beside the text, so the bundle is 4 files you can review in full before installing.

Install

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

# Layout-Preserving PDF Translation · 2.7k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/layout-preserving-pdf-translation/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/layout-preserving-pdf-translation" ] && { [ ! -e .claude/skills/layout-preserving-pdf-translation ] || { mv .claude/skills/layout-preserving-pdf-translation "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/layout-preserving-pdf-translation" .claude/skills/ && echo "Installed .claude/skills/layout-preserving-pdf-translation"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add ghbhiee/layout-preserving-pdf-translation

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/layout-preserving-pdf-translation/ 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/layout-preserving-pdf-translation/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/layout-preserving-pdf-translation" ] && { [ ! -e ~/.claude/skills/layout-preserving-pdf-translation ] || { mv ~/.claude/skills/layout-preserving-pdf-translation "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/layout-preserving-pdf-translation" ~/.claude/skills/ && echo "Installed ~/.claude/skills/layout-preserving-pdf-translation" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/layout-preserving-pdf-translation/ 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 pdf-translate in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, layout-preserving-pdf-translation.

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
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceghbhiee/layout-preserving-pdf-translation

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

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