OCR and Documents
Use this skill when a document is not directly machine-readable.
Preferred Flow
- Determine whether the file is text-native or scanned.
- Run OCR first when the text layer is missing or broken.
- Preserve page order, tables, and obvious headings where possible.
- Only after extraction should you summarize or transform the content.
Guardrails
- State clearly when OCR confidence is low.
- Do not fabricate unreadable text.