doc-intelligence-promotion - Document extraction post-processing pipeline
Post-process extracted documents: convert tables to CSV, generate calc reports, extract charts metadata
Tags
Updated: 2026-03-22Capabilities
Typical Inputs
Typical Outputs
What this skill does
- read document
- export table to CSV
- validate calc report input
- extract chart metadata
- generate HTML report
Inputs
- PDF or DOCX document
- extraction manifest
- domain configuration
Outputs
- CSV data table
- HTML calc report
- chart metadata YAML
Requirements
- Python environment
- pdfplumber library
- PyMuPDF library