Pdfvision

Extract text, metadata, per-page density signals, layout, image boxes, OCR, and page PNGs from a PDF via the pdfvision CLI. Use when the input is a `.pdf` URL, a local PDF path, or a PDF another agent skill produced. Triggers on: 'read this pdf', 'extract from <file>.pdf', '.pdf', 'scan / slide / paper / form contents'.

yamadashy Updated 8 repo stars
Without pdfvision, an agent hauls every page as an image and still can't read the table. With pdfvision it searches, renders one region, verifies, and answers w

File contents

yamadashy/pdfvision commit 4dae2df9f7

Frequently asked questions

npx get-skill add yamadashy/pdfvision