Geoai Skills

geoai-skills

A Claude Code plugin that adds GeoAI-powered skills for geospatial data exploration, satellite imagery download, AI-based object detection, and session memory.

Built on the GeoAI Python library.

Installation

From GitHub

Add the repository as a plugin source and install:

This registers the GitHub repo as a marketplace and installs the plugin. Skills will be available as /geoai-skills: in all future sessions.

Updating

To pull the latest version, update the marketplace first and then the plugin:

Prerequisites

- Python 3.10+ with the geoai-py package installed (pip install geoai-py)
- For AI models (object detection, segmentation): PyTorch with CUDA (optional, CPU works but is slower)
- For Overture Maps data: pip install "geoai-py[extra]"

Skills

inspect-geo

Inspect any raster or vector geospatial file -- CRS, bounds, bands, resolution, dtype, attribute summaries, and band statistics. Supports GeoTIFF, Shapefile, GeoJSON, GeoPackage, GeoParquet, and more.

download-data

Download NAIP aerial imagery for a bounding box. Specify coordinates as minx,miny,maxx,maxy in WGS84 and optionally a year.

search-stac

Search and download satellite imagery from Microsoft Planetary Computer. Browse collections, search by bbox and time range, and download items.

overture-data

Download Overture Maps data (buildings, places, roads, land use, water, etc.) for a bounding box.

process-raster

Process raster data: clip by bounding box, stack multiple bands, mosaic GeoTIFFs, or convert between raster and vector formats.

detect-objects

Run pre-trained AI models on geospatial imagery. Detect buildings, cars, ships, solar panels, or use text-prompted segmentation with GroundedSAM.

read-memories

Search past Claude Code session logs to recover context from previous…