What problem does it solve? Getting usable text out of PDFs and scanned documents is inconsistent: some files are text-based, others are scanned images requiring OCR, and choosing the wrong tool wastes time or fails entirely. This Skill provides a decision workflow that routes each document to the right extractor. ## Core Features & Use Cases - Tiered extraction strategy: Try web_extract first for remote URLs, then pymupdf for lightweight local extraction, then marker-pdf for OCR, equations, forms, and complex layouts. - Full PDF operations: Extract text, Markdown, tables, embedded images, and metadata, plus split, merge, and search PDFs using pymupdf alone. - High-quality OCR: marker-pdf handles scanned documents in 90+ languages, LaTeX equations, and reading-order detection, with optional LLM-boosted accuracy. - Use Case: You receive a scanned contract PDF. The Skill checks disk space, runs marker-pdf OCR, and returns clean Markdown with the document's structure preserved. ## Quick Start Extract the text from the attached scanned PDF and convert it to Markdown, using OCR if the document has no text layer.
