pdf-conversion-router - Route PDFs to faithful conversion outputs
Classifies PDFs, selects conversion routes and settings, validates representative sections, and repairs noisy outputs.
Tags
Updated: 2026-09-29Capabilities
What this skill does
- Classify source PDFs
- Classify target outputs
- Choose extraction routes
- Select conversion settings
- Validate representative sections
- Repair noisy outputs
- Run OCR before conversion
Inputs
- PDF file
- Target output format
- Conversion fidelity requirements
Outputs
- Converted document
- Validated output structure
- Cleaned conversion output
Requirements
- OpenDataLoader PDF CLI
- OCR capability for scanned PDFs
- pdfinfo and pdftotext utilities
