Extracting Pdf Text

A well-organized toolkit for getting text out of PDFs and into your LLM pipeline. It's basically a decision tree with scripts: PyMuPDF for standard PDFs, pdfplumber when tables matter, pytesseract for local OCR, and Mistral's API when you need serious accuracy on scanned documents. The pragmatic approach here is refreshing. Start with the fast option, escalate only if needed. With 257 installs and clean audit scores, it's seeing real use. If you're building RAG systems or need to parse documents regularly, this gives you the right tool for each situation without overthinking it.

Install to Claude Code

npx -y skills add letta-ai/skills --skill extracting-pdf-text --agent claude-code