Published skills
detect-objects
Run pre-trained AI models on geospatial imagery. Detect buildings, cars, ships, solar panels, agriculture fields, or use text-prompted segmentation with GroundedSAM. Requires GPU for best performance.
install-geoai
Verify that the geoai Python package is installed and functional. If not, provide installation instructions. Optionally check extra dependencies for deep learning models.
process-raster
Process raster data: clip by bounding box, stack multiple bands, mosaic GeoTIFFs, or convert between raster and vector formats.
download-data
Download NAIP aerial imagery for a bounding box. Specify coordinates as minx,miny,maxx,maxy in WGS84 and optionally a year.
overture-data
Downloads Overture Maps data (buildings, places, roads, land use, water, etc.) for a bounding box. Returns a GeoDataFrame saved as GeoJSON or GeoPackage.
inspect-geo
Inspects any raster or vector geospatial file, returning CRS, bounds, bands, resolution, dtype, attribute summaries, and band statistics. Supports GeoTIFF, Shapefile, GeoJSON, GeoPackage, GeoParquet, and more.
search-stac
Search and download satellite imagery from Microsoft Planetary Computer. Browse available collections, search by bounding box and time range, list assets, and download specific items.
read-memories
Searches past Claude Code session logs to recover context from previous conversations, including past decisions, data paths, CRS info, model configurations, and unresolved work. It operates across all projects or can be scoped to the current one.
Category alert