All skills

OCR Document Processor

Extract text from images and scanned PDFs using OCR

v1.0.0 Skill dkyazzentwatwa /rvanbaalen:ocr-document-processor Source
/plugin install ocr-document-processor@rvanbaalen

When to use

Use when you need to extract text from images, scanned PDFs, or photographs. Supports over 100 languages, table detection, and structured output formats.

How it works

  1. Reads the input file (PNG, JPEG, TIFF, BMP, or PDF)
  2. Runs OCR with language detection
  3. Returns extracted text with confidence scoring
  4. Optionally structures output as markdown, JSON, or HTML

Capabilities

  • Image OCR — extract text from PNG, JPEG, TIFF, BMP
  • PDF OCR — process scanned PDFs page by page
  • Multi-language — supports 100+ languages
  • Table detection — extract tabular data to CSV/JSON
  • Batch processing — handle multiple documents at once
  • Quality assessment — confidence scoring for results

Invoke

/rvanbaalen:ocr-document-processor