Histolab

This is a Python toolkit for working with whole slide images in digital pathology, the kind of gigapixel H&E or IHC stained tissue scans you get from microscopy. It handles the annoying parts: loading various WSI formats (SVS, TIFF, NDPI), automatically detecting tissue regions versus background, and extracting tiles in sensible ways (random sampling, grid coverage, or scored by nuclei density). The tile extraction strategies are well thought out. RandomTiler for quick sampling, GridTiler for full coverage, ScoreTiler when you want the most informative regions based on cellular content. If you're building computational pathology datasets or preprocessing slides for deep learning pipelines, this handles the boilerplate so you can focus on the actual analysis.

Install to Claude Code

npx -y skills add davila7/claude-code-templates --skill histolab --agent claude-code