pdf-extraction
Installation
SKILL.md
PDF Extraction (auto text / OCR)
Extract content from PDFs without deciding whether each page is selectable text or a scan.
| Page type | Tool |
|---|---|
| Native text | pdfplumber (text + tables) |
| Scanned / image | PyMuPDF + Tesseract OCR |
Install
# System OCR engine (required for scanned pages)
# Ubuntu/Debian:
sudo apt install tesseract-ocr tesseract-ocr-eng
# Optional Traditional Chinese:
# sudo apt install tesseract-ocr-chi-tra