pdf-translate

pdf-translate is a skill for Claude Code, Codex from JaeHyeon-KAIST/pdf2zh-next-mcp. It costs 145 tokens per session (1,739 once invoked), scanned A, original, MIT.

A tool-assisted workflow for translating an entire PDF document into a new PDF in another language. A PDF is a fixed-layout document commonly used for papers, reports, manuals, and other files.

In plain words
What is it for?
Use it to translate papers, reports, manuals, and other PDF documents into a specified target language.
Why use it?
It handles translation from a local file path without requiring the PDF to be uploaded in the chat. The workflow also tracks extraction and translation progress across the document.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/me/paper.pdf.

Good fit Use it to translate papers, reports, manuals, and other PDF documents into a specified target language.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pdf-translate

README.md
[![agentmods](https://agentmods.dev/badge/skills/jaehyeon-kaist/pdf2zh-next-mcp/skill/github.svg)](https://agentmods.dev/skills/jaehyeon-kaist/pdf2zh-next-mcp/skill)
Your own site
<a href="https://agentmods.dev/skills/jaehyeon-kaist/pdf2zh-next-mcp/skill"><img src="https://agentmods.dev/badge/skills/jaehyeon-kaist/pdf2zh-next-mcp/skill/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.

agentmods 80×15 button for pdf-translate

Your own site · 80×15
<a href="https://agentmods.dev/skills/jaehyeon-kaist/pdf2zh-next-mcp/skill"><img src="https://agentmods.dev/badge/skills/jaehyeon-kaist/pdf2zh-next-mcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,739 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00145 $0.01739
Opus 5 $0.00072 $0.00870
Sonnet 5 $0.00029 $0.00348
Haiku 4.5 $0.00015 $0.00174

Measured 11d ago against content hash ce06ad4084b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pdf-translate 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 11d 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.

skill/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Translate Skill

pdf-translate MCP 서버를 사용하여 PDF 문서를 번역된 PDF로 변환하는 스킬이다. 이 MCP는 사용자의 로컬 머신에서 동작하므로, 파일 경로만 있으면 PDF를 업로드받지 않아도 번역할 수 있다.

핵심 원칙

  • 사용자가 파일 경로를 제공하면 바로 번역을 진행한다.
  • 파일이 존재하는지 확인하려고 시도하지 않는다. MCP가 로컬에서 직접 접근한다.
  • 경로를 그대로 extract_segmentsfile 파라미터에 전달한다.
  • 중요: file 파라미터에는 반드시 사용자가 메시지에 입력한 로컬 절대 경로를 사용한다. 첨부 파일의 내부 경로(/mnt/user-data/uploads/...)는 MCP 서버에서 접근할 수 없으므로 절대 사용하지 않는다.

번역 워크플로우 (5단계)

모든 MCP 호출은 비동기이다. check 툴은 내부에서 대기 후 결과를 반환하므로, 진행 중 응답이 오면 바로 다시 호출하면 된다.

1단계: 세그먼트 추출 시작

pdf-translate:extract_segments 호출:

파라미터 설명 기본값
file PDF 절대 경로 (사용자 제공 그대로) 필수
lang_in 원본 언어 en
lang_out 번역 대상 언어 ko
output_dir 출력 디렉토리 (비우면 원본과 같은 위치) ""
pages 번역할 페이지 범위 (예: '1-7,10'). 아래 "페이지 제외 처리" 참고. "" (전체)

반환값: session_dir (세그먼트는 포함되지 않음, 비동기 처리)

2단계: 추출 완료 확인

pdf-translate:check_extraction_status 호출. 서버가 내부에서 대기 후 응답하므로 별도 대기 불필요.

파라미터 설명 기본값
session_dir 1단계에서 받은 세션 디렉토리 경로 필수
offset 세그먼트 시작 인덱스 0
  • status: "extracting" → 아직 진행 중. 바로 다시 호출.
  • status: "done" → 완료. 세그먼트와 번역 instruction 포함.
  • has_more: true → 세그먼트가 더 있음. offset을 늘려서 다시 호출.

3단계: 세그먼트 번역

반환된 세그먼트를 Claude가 직접 번역한다.

필수 규칙:

  • {v0}, {v1} 같은 수식 플레이스홀더는 절대 건드리지 않는다. 그대로 유지한다.
  • MCP가 반환하는 instruction이 있다면 그것을 우선적으로 따른다.
  • 전체 세그먼트를 먼저 훑어 용어를 파악하고, 일관된 용어를 사용한다.

번역 완료 후, save_translated_segments(session_dir, segments_json) 툴을 호출하여 저장한다. 여러 번 호출하면 누적 저장된다.

4단계: 번역 PDF 조립 시작

pdf-translate:assemble_translated 호출:

파라미터 설명
session_dir 1단계에서 받은 세션 디렉토리 경로
glossary_json (선택) 용어집 JSON 문자열

비동기로 실행됨. 즉시 반환.

5단계: 조립 완료 확인

pdf-translate:check_assembly_status 호출. 서버가 내부에서 대기 후 응답.

파라미터 설명
session_dir 세션 디렉토리 경로
  • status: "assembling" → 아직 진행 중. 바로 다시 호출.
  • status: "success" → 완료. 출력 PDF 경로 포함.

완료되면 출력 PDF 경로를 사용자에게 알려준다.

Read the full file on GitHub · 150 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 11d ago First seen · 150 lines · 145 tokens per session scan A ce06ad4084b5

Subscribe to this mod's changes

pdf-translate is a skill published in the GitHub repository JaeHyeon-KAIST/pdf2zh-next-mcp (3 stars, last pushed 5mo ago), licensed MIT. It adds 145 tokens to every session and 1,739 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

translate-book

Translate books (PDF/DOCX/EPUB) into any language using parallel sub-agents. Converts input -> Markdown chunks -> translated chunks -> HTML/DOCX/EPUB/PDF.

deusyu/translate-book · 42 tokens

pdf_translator

Extract text from PDF files, translate it to a target language, and save the result as a Markdown file. Use this skill when the user wants to translate a PDF document or asks to "convert PDF to Chinese".

ForceInjection/AI-fundamentals · 47 tokens

docutranslate

Use when translating documents locally via LLM — PDF, Word, Excel, Markdown, SRT subtitles with format preservation. DocuTranslate: LLM-powered multi-format local file translation tool with MCP server support.

znlgis/opengis-skills · 47 tokens

lov-academic-translator

A tool for translating English research papers, journal or conference articles, arXiv papers, and technical PDFs into Chinese PDFs or publishable Chinese Markdown. It can preserve requested images, formulas, page matching, and layout details.

lovstudio/skills · 87 tokens

hebrew-document-generator

Generate Hebrew documents (PDF, DOCX/Word, PPTX) with correct right-to-left layout, mixed Hebrew-and-English bidi handling, and Hebrew typography. Use whenever the output is a Hebrew or mixed Hebrew/English Word document, Hebrew PDF, or Hebrew PowerPoint ("Hebrew Word document", "מסמך Word בעברית", "create a .docx in…

skills-il/localization · 247 tokens

pdf-translate

Translate local PDFs, including safe prose on image-only scans, into Vietnamese or another supported Latin-script language while preserving layout, formulas, tables, and figures. Use for PDF translation, OCR-assisted scan translation, batch translation, terminology-sensitive handoff translation, or diagnosing…

breslee1707/VI-Translate · 77 tokens