Turn your images and scans into readable text.
What it does
Extracts readable text from images and PDFs, with custom prompts for interpreting their contents.
When to use it
Use when text needs to be read from screenshots, photos, scanned documents, or other image files.
How to use it
Give it an image or PDF path; it returns extracted text or analysis.
What you provide
- an image or PDF path
- Your files
Uses
Latest review
What you need · 8
The documented setup requires macOS on Apple Silicon or Intel.
The deployment guide requires Python 3.8 or newer.
Access · 7
This skill
Ollama
Execute
Installs and starts Ollama
Write
Sends images to Ollama
deepseek-ocr
Execute
Downloads the OCR model