PDF To Markdown

Convert PDF inputs into clean, reusable whole-document Markdown for agents, LLM ingestion, search, or archival text, using Xberg with safe output handling, Korean scan OCR, page markers, validation, and layout escalation. Use when the user asks to create, save, generate, normalize, reconvert, or extract a Markdown or whole-document agent-readable text artifact from a PDF. Do not use for summaries or questions with no converted artifact, PDF editing or rendering, parser research, or targeted extraction into CSV, JSON, images, or other structured formats.

sjunepark Updated 1 repo stars

File contents

sjunepark/agent-scripts commit 52554916c0

Frequently asked questions

npx get-skill add sjunepark/pdf-to-markdown