STOP. READ THIS ENTIRE SKILL.MD BEFORE CALLING ANY ENDPOINT.

/extract-pdf

Rust-native PDF extraction engine via pdf_oxide. MIT-licensed replacement for PyMuPDF across the Embry OS pipeline.

Quick Start

# Extract a single PDF (full pipeline: profile + blocks + sections + tables + figures)
./run.sh extract document.pdf

# Extract with JSON output to directory
./run.sh extract document.pdf --output-dir ./results/

# Survey a PDF (lightweight profiling — no full extraction)
./run.sh survey document.pdf