What problem does it solve? Getting usable text out of PDFs and scanned documents is inconsistent: text-based PDFs need a lightweight parser, while scanned pages, equations, and complex layouts require full OCR. This Skill routes each document to the right extractor so you get clean text or Markdown without guessing which tool fits. ## Core Features & Use Cases - Tiered extraction: Try web_extract for remote URLs first, then pymupdf for text-based PDFs, then marker-pdf for scanned documents, equations, forms, and complex layouts. - Structured output: Extract plain text, Markdown, tables, embedded images, and document metadata, with page-range selection for large files. - PDF utilities: Split, merge, and search PDFs natively with pymupdf, no extra dependencies. - Use Case: You receive a scanned 40-page lab report as a PDF. The Skill detects that the text layer is empty, checks disk space, and runs marker-pdf OCR to produce Markdown with equations and tables intact. ## Quick Start Extract the text from the attached PDF report.pdf, using OCR if any pages are scanned images.
