Pdf To Markdown

Converts PDFs to Markdown with automatic detection of whether you're dealing with native text or scanned documents. Uses @opendocsg/pdf2md under the hood for native PDFs, which is fast and handles basic table structure. The OCR path for scanned docs isn't implemented yet, so you'll just get a warning if your PDF needs it. Auto mode checks the first page for extractable text and routes accordingly. Multi-column layouts won't survive perfectly, and you'll need to run npm install in the skill directory first. Straightforward tool for the common case of extracting content from text-based PDFs without reaching for heavier Python solutions.

Install to Claude Code

npx -y skills add duc01226/easyplatform --skill pdf-to-markdown --agent claude-code