PDF to Markdown Converter

概要

This skill enables Claude to efficiently process and ingest complete PDF documents by converting them into highly structured Markdown. Unlike basic text extraction, it preserves critical document elements such as hierarchical headers, complex tables, lists, and multi-column layouts. It also automatically extracts and manages images, allowing for direct visual analysis of charts and diagrams. With a high-accuracy mode powered by IBM's Docling for complex tables and an aggressive caching system for instant subsequent loads, it provides a robust solution for deep document analysis and full-context comprehension within Claude.

主な機能

• Preservation of document structure including headers, tables, lists, and multi-column layouts
• Aggressive caching system for instant re-processing of previously analyzed PDFs
• Standardized Markdown output with metadata headers and image summary tables
• Automatic image extraction with relative path referencing and visual analysis support
• High-accuracy AI-powered mode for extracting complex and borderless tables
• 0 GitHub stars

ユースケース

• Loading entire research papers or manuals into context for comprehensive analysis
• Extracting complex data from financial reports or medical documents with high precision
• Performing visual analysis on charts, diagrams, and figures contained within PDFs