What problem does it solve? Getting usable text out of PDFs is inconsistent: text-based PDFs need a lightweight parser, while scanned documents, 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 strategy: Try web_extract for remote URLs first, then pymupdf for text-based PDFs, then marker-pdf for scanned documents, OCR in 90+ languages, equations, and complex layouts. - Structured output: Extract plain text, Markdown, tables, embedded images, and document metadata, with page-range selection for targeted extraction. - PDF utilities: Split, merge, and search PDFs natively with pymupdf, plus disk-space checks before installing the multi-gigabyte marker-pdf stack. - Use Case: You receive a scanned 40-page report as a PDF. The Skill detects that the text layer is empty, verifies disk space, and runs marker-pdf OCR to produce clean Markdown with tables and reading order preserved. ## Quick Start Extract the text from the attached scanned report.pdf into Markdown, using OCR if the pages have no text layer.
