A sophisticated translation engine that preserves complex document layouts by leveraging LaTeX reconstruction and direct arXiv source integration.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pdf-translate-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install pdf-translate-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is PDF Translator?
The PDF Translator is a high-performance Openclaw Skills utility designed to bridge the gap between static documents and multilingual accessibility. Unlike standard OCR tools, this skill understands the structural integrity of a document, utilizing two distinct workflows to ensure that translated outputs maintain the original visual context, column structures, and embedded imagery.
By combining multimodal vision analysis with professional LaTeX typesetting, it serves as an end-to-end pipeline for researchers and professionals. Whether processing a local file or pulling directly from the arXiv repository, the skill ensures that technical terms, mathematical formulas, and bibliographies remain intact and professionally formatted.
PDF Translator Use Cases
- Translating academic arXiv papers into Chinese or other languages while preserving original TeX formatting.
- Converting local business reports and technical manuals into translated PDFs with identical layout structures.
- Automating the extraction and translation of embedded text in image-heavy PDF documents.
- Reconstructing complex multi-column document layouts into editable LaTeX formats.
How PDF Translator Works
- Input Detection: The skill identifies if the source is a local PDF file or an arXiv ID/URL.
- Source Acquisition: For arXiv, it downloads the original TeX source; for local files, it converts pages into high-resolution images for analysis.
- Content Extraction: It extracts text, images, and layout metadata, identifying non-translatable elements like math formulas and citations.
- Multimodal Translation: The AI translates text blocks while preserving LaTeX markup or structural hierarchy.
- LaTeX Reconstruction: It generates or modifies LaTeX code to wrap the translated content in a format that mirrors the original document.
- Multi-Pass Compilation: The system runs XeLaTeX three times to resolve all cross-references, citations, and bibliographies into a final PDF.
PDF Translator Setup
To utilize this skill within the Openclaw Skills ecosystem, ensure the following dependencies are installed:
# Install Python dependencies
pip install pymupdf pillow requests
# Install TeX Live (Debian/Ubuntu)
sudo apt install texlive-xetex texlive-lang-chinese
# Install TeX Live (macOS)
brew install mactex
PDF Translator Data Schema & Taxonomy
The skill manages data through a structured working directory to ensure traceability and easy debugging:
| Component | Description |
|---|---|
pages/ |
High-quality PNG renders of each PDF page (150 DPI). |
extracted/ |
Individual image assets extracted from the original PDF. |
manifest.json |
Metadata containing page dimensions and layout coordinates. |
translated.tex |
The final generated LaTeX source file. |
output.pdf |
The compiled, translated document. |
PDF Translator Advanced Features
- Direct arXiv Integration: Automatically fetches and unpacks .tar.gz source files for pixel-perfect academic translation.
- Multi-Pass Resolution: Built-in triple-pass compilation logic to ensure
\citeand\reftags are never broken. - Multimodal Layout Analysis: Uses vision-based AI to detect multi-column shifts and complex header/footer patterns.
- Chinese Language Optimization: Native support for the
ctexpackage and XeLaTeX engine for high-quality Asian character rendering. - Intelligent Fallback: Automatically switches to image-based layout reconstruction if TeX source files are unavailable.
SKILL.md
Loading
Related Openclaw Skills
Mind-Wander
An autonomous background reasoning agent that explores open questions and hypotheses using local models without consuming your primary token budget.
Hyperliquid Names (HLN) API
An AI agent skill designed to interact with the Hyperliquid Names API for domain resolution, profile lookups, and HyperEVM integration.
Awesome Closet Stylist
A high-autonomy AI agent skill that transforms your digital wardrobe into a personal stylist through natural language interaction and intelligent outfit planning.
Capability Evolver
A recursive self-evolution engine that allows AI agents to autonomously analyze their runtime history, fix bugs, and optimize their own source code.
Graph-RAG Memory Skill
A temporal Graph-RAG system providing AI agents with persistent, queryable long-term memory through a Mixture-of-Experts knowledge graph architecture.
SQL Database Toolkit
A comprehensive data analysis suite that integrates database connectivity, SQL execution, interactive visualization, and AI-powered report generation.
Featured*
