ocr-and-documents

To extract text and tables from scanned PDFs and office files, you can use this skill to perform high-fidelity OCR with layout analysis. It processes diverse formats including DOCX, PPTX, and XLSX, converting complex document structures into clean, accessible data for further analysis.

The best way to convert research papers into clean Markdown files is using this skill's batch extraction capabilities. By utilizing the high-quality OCR engine, it parses complex layouts and metadata from scanned documents, outputting structured Markdown that preserves the original document's formatting.

Yes, this OCR text extraction tool supports lightweight parsing for simple PDF documents. You can choose the lightweight text extraction method using the pymupdf engine to quickly pull raw text without invoking the heavier layout analysis required for complex scanned documents.

Yes, you can batch extract specific table data from financial reports in XLSX and PDF formats. The skill intelligently isolates tabular data across various document types, allowing you to retrieve structured table information for immediate use in data analysis workflows.

Yes, you need Python document processing libraries to perform OCR and metadata retrieval. This skill depends on pymupdf, pymupdf4llm, marker-pdf, and pandas to execute its text extraction, layout analysis, and batch processing functions effectively.

You should use high-fidelity OCR with layout analysis instead of standard text extraction when processing scanned PDFs or documents with complex structures. This approach ensures accurate data capture from images and intricate layouts that lightweight text parsing cannot interpret correctly.