pdf-translate

What This Skill Does

The pdf-translate skill is a robust, professional-grade solution designed to convert PDF documents into high-quality, professionally formatted Chinese versions. Moving beyond simple text extraction, this skill employs a sophisticated 'Markdown-first' workflow. It parses the source document into structured Markdown, ensuring that headings, tables, lists, and code blocks retain their logical hierarchy. Once the content is translated to professional-standard Chinese—adhering to rigorous translation guidelines that prevent 'translation-speak'—the skill uses the powerful weasyprint engine to re-render the content into a polished, print-ready PDF. It features full CJK (Chinese, Japanese, Korean) support, ensuring that even technical documents with code blocks display correctly without character corruption.

Installation

To install this skill, use the following command in your OpenClaw terminal: clawhub install openclaw/skills/skills/chrislee121/pdf-translate

Ensure that you have the necessary system dependencies installed based on your operating system, specifically Pango for font rendering, and the required Python packages: pdfplumber, markdown, and weasyprint.

Use Cases

This skill is perfect for researchers, developers, and professionals who need to consume English-language documentation, whitepapers, or technical manuals in Chinese. It is specifically optimized for technical content containing code snippets, data tables, and complex formatting that would typically break in automated translators. Whether you are localized technical manuals for a team or simply trying to digest a long report, this tool preserves document intelligence through every step of the transformation process.

Example Prompts

1. "Could you please translate this technical manual into Chinese for me?"
2. "翻译PDF: please handle this document and keep the formatting for the code blocks and tables."
3. "I need to translate this research paper to Chinese. Can you make sure the headings and structure stay the same?"

Tips & Limitations

• Translation Quality: The skill follows a 'three-step' translation workflow. For best results on complex documents, ensure the source PDF has clear text layers rather than scanned images.
• Formatting: Always ensure you have sufficient disk space for the generated Markdown and PDF files. The tool relies on system fonts; ensure you have CJK fonts installed for optimal typography.
• Large Files: For documents exceeding 20 pages, the skill handles extraction in segments. Do not interrupt the process once it has begun.
• Troubleshooting: If you encounter rendering issues on macOS, remember to use the DYLD_FALLBACK_LIBRARY_PATH environment variable as specified in the documentation to help the system locate required library files.