Stats
Actions
Tags
From document-to-markdown
Use when you have a scanned PDF with no embedded text layer and need to add OCR text
How this skill is triggered — by the user, by Claude, or both
Slash command
/document-to-markdown:ocr-scanned-pdfThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Add text recognition to image-only PDFs using `ocrmypdf`. This preprocesses scanned documents to make them readable by text-extraction tools.
Add text recognition to image-only PDFs using ocrmypdf. This preprocesses scanned documents to make them readable by text-extraction tools.
pdf-to-markdown on a scanned document--lang (optional; defaults to eng)--out (optional; defaults to <stem>-ocr.pdf next to source)pdftotext -layout <pdf> -. If output is substantial, warn the user that OCR may be unnecessary.ocrmypdf with sensible defaults: ocrmypdf --language=<lang> <input-pdf> <output-pdf>, where language defaults to eng if not specified.--force-ocr (OCR even if text layer exists), --redo-ocr (re-OCR if a layer already exists).<stem>-ocr.pdf next to the source.npx claudepluginhub danielrosehill/claude-code-plugins --plugin document-to-markdownCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.