Slide Viewer
Explore whole-slide microscopy, digital pathology, and spatial transcriptomics.
Explore real tissue images and spatial measurements in one research workspace. Open compatible SVS, TIFF, DICOM, OME-Zarr or AnnData sources; navigate image pyramids, compare registered gene expression, inspect cells and molecules, adjust microscopy channels, and edit annotated regions. Use source-backed scientific workflows and single-user projects while preserving the original specimen. UI actions have typed agent counterparts; availability depends on the source and host. Read current selections and annotations on demand, and capture the current viewport or a source region for image interpretation. Research use, not clinical diagnosis.
Runs locally: needs the ChatGPT desktop app or Codex with local execution enabled.
Install
- 1Add it in ChatGPT
Open Plugins in the ChatGPT sidebar (web or desktop), search for “Slide Viewer” and select +. You'll be asked to sign in to any connected service on first use. Then type @ in a chat to call it.
Skills 1
- slide-viewer
Open and control whole-slide microscopy, supported DICOM/OME-Zarr and spatial AnnData sources; inspect live state, registered molecular layers, single-user projects and bounded source-backed research workflows.
Things to ask
- “Download OpenSlide’s full CMU-1 brightfield slide (132.6 MB), open it, and ask me to draw a region before inspecting tissue.”
- “Download Squidpy’s H&E mouse-brain crop, open its registered tissue image, and inspect the real spot and gene counts.”
- “Download Squidpy’s fluorescence mouse-brain crop and compare Slc17a7/Gad1 over its registered tissue preview, if present.”