Who it is forSomeone whose book PDF is a scan without selectable text.
The problemScanned PDFs have no extractable text.
The outcomeA text-searchable PDF ready to convert.
What you need first
- An agent that supports skills
- OCR (ocrmypdf) for scanned PDFs
Steps
- Install ocrmypdf
- Run ocrmypdf input.pdf output.pdf
- Run Book to Skill on output.pdf
- Check the extracted chapters
Prompt for your agent
OCR <scan.pdf> with ocrmypdf, convert the result with book-to-skill, and report the number of chapters extracted.
Caveat. OCR quality limits the quality of the generated skill.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for virgiliojr94/book-to-skill and "Prepare a scanned PDF before converting it"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer