MinerU PDF Parser
A Clawdbot skill for parsing PDFs locally using MinerU with CPU processing. Produces rich structured output including Markdown, JSON with layout data, and extracted images without requiring GPU resources.
🚀 Extract structured data from PDFs effortlessly with MinerU PDF Parser. This Clawdbot skill runs locally on your CPU—no GPU needed—and converts PDFs into rich Markdown, detailed JSON with layout data, and extracted images. Perfect for automating document processing workflows.
💡 Ideal for projects requiring accurate text extraction, layout preservation, and image recovery from complex PDFs. Whether you're building document analysis tools, data pipelines, or content management systems, this skill handles tables, multi-page documents, and maintains structural integrity.
✨ Fully configurable with flexible language support, threading options, and customizable output formats. Process documents locally for privacy and speed without external API dependencies.
Requirements
MinerU CLI tool for PDF parsing and extraction
Clawdbot framework for skill integration