Source: https://github.com/aipoch/medical-research-skills

Validation Shortcut

Run this minimal command first to verify the supported execution path:

python scripts/extract_pdf.py --help

When to Use

Converting a PDF report/paper into Markdown while preserving page structure (## Page XX) for easy navigation.
Preparing PPT or design materials where you need both extracted text and page screenshots/blocks (tables, figures, diagrams).
Reviewing scanned or mixed PDFs and filtering out "text-only" screenshots to keep only meaningful visuals.
Building a dataset for downstream analysis where each page's text and images must be linked and traceable.
Creating a lightweight "PDF-to-Markdown" archive with per-page headings and image references.