Your documents, parsed with text coordinates.
Extracts text with page coordinates from local documents and creates page images for visual analysis.
When to use it
Use for local document extraction, layout-aware text analysis, OCR, page screenshots, batch ingestion, or selected and password-protected PDF pages.
Give it document files; it extracts layout-preserved text or saves structured JSON and Markdown locally.
What you provide
Requires Python 3.10+ for the Python installation and bundled batch-processing script.
Required when processing Office formats; PDF and supported image inputs do not require it.
This skill
GitHub
Downloads missing OCR language data
arXiv
Fetches the publisher's paper record