PDF Extract

Extract structured data from PDFs using schema-driven field extraction. Use this skill when the user asks to "extract data from PDFs", "parse property reports", "extract fields from documents", "create a schema for extraction", or when you need to convert unstructured PDFs into structured JSON. Supports single file extraction, batch processing with glob patterns, and exploration mode for schema development.

soapboxbuild Updated 0 repo stars

File contents

soapboxbuild/audette-skills commit 8c09abb0de

Frequently asked questions

npx get-skill add soapboxbuild/pdf-extract