AI Agent Skills

This tool has been deprecated. Use Agentic Document Extraction instead.

Python library for Agentic Document Extraction (ADE).

newspaper3k is a news, full-text, and article metadata extraction in Python 3. Advanced docs:

OCR & Document Extraction using vision models

📄 PDF extraction and rendering across all JavaScript runtimes

Simple PDF text extraction

Speaker is a Codex skill project for academic presentations: read real.pptx, combine text extraction, PPTX structure parsing, page-by-page rendering, OCR, and visual rev…

MITIE: library and tools for information extraction

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications