tanis90tanis90Community·1 Agent Skills Included

pdf-converter-mineru

Convert PDFs and documents to Markdown, Word, HTML

Converts PDFs, images, and Office documents into Markdown, Word, HTML, LaTeX, or plain text. Handles OCR for scanned documents and recognizes tables, formulas, and layouts across 80+ languages. Offers a fast no-auth mode for quick reads and a full-fidelity mode for large files and batch jobs. Eliminates manual copy-pasting and reformatting when extracting content from documents.
npx skills add tanis90/pdf-converter-mineru --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install pdf-converter-mineru?

Run `npx skills add tanis90/pdf-converter-mineru --all -g -y` in your terminal to install the skill globally.

How to convert a PDF to Word or Markdown?

Just ask in plain language, like 'convert report.pdf to Word'. The skill uses MinerU to output Markdown, DOCX, HTML, LaTeX, or plain text.

Can it handle scanned documents and OCR?

Yes. It runs OCR on scanned PDFs and images, and supports over 80 languages with a simple language flag.

Do I need an API key to use it?

No. The flash-extract mode works without any key for files up to 10 MB or 20 pages. Run `mineru-open-api auth` to unlock the full extract mode for larger files.

Can it extract tables and formulas from papers?

Yes. The extract mode preserves tables, images, and LaTeX formulas, and your agent can then summarize or pull out specific sections on request.

Related Repositories in Content & Communication

View All in Content & Communication