geospatial-skills

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.

1 skill

This skill should be used when working with GDAL command line tools for raster and vector geospatial processing. Covers inspection, reprojection, clipping, raster conversion, mosaics, tiling, rasterization, and COG creation.

1 skill

This skill should be used when working with gpio for GeoParquet inspection, validation, optimization, and distribution. Covers GeoParquet best practices using gpio CLI and DuckDB.

1 skill

This skill should be used when building map-centric demo webapps with MapLibre globe, DuckDB-WASM, and a warm dark HUD aesthetic. Covers satellite imagery retrieval demos, embedding visualization tools, geospatial search UIs, and map-first data exploration frontends.

1 skill

This skill should be used when viewing, previewing, or inspecting geospatial files from the command line. Covers interactive raster viewing (viewtif), interactive vector viewing (viewgeom), and non-interactive terminal-inline viewing (viewinline).

1 skill

GeoZarr conventions for geospatial Zarr stores: CF grid_mapping, coordinate arrays, Zarr v2/v3 dimension declarations, multiscales, proj:/spatial: namespaces, and xarray/rioxarray/GDAL interop.

1 skill

Download Overture Maps data (buildings, places, roads, land use, water, etc.) for a bounding box. Returns a GeoDataFrame saved as GeoJSON or GeoPackage.

1 skill

Parallelize large-scale geospatial operations on a single fat node — tile-edge dissolve, polygon elimination, polygonize, spatial joins, reprojection, simplification — at national/continental scale (10–100M polygons). Use when speeding up or designing a geospatial batch process, or as a pre-flight checklist for known failure modes (DuckDB GEOS segfaults, topology exceptions, int64 overflow, NFS thrashing).

1 skill

Download PlanetScope imagery at scale (hundreds to 100k+ AOIs) via the Planet Python SDK v2. Covers search/activate/extract phases, COG /vsicurl/ vs Orders API, GDAL config for signed URLs, retry logic, concurrency budgets, and Planet-side gotchas (broken activations, cold-storage thaw tails, dead assets). Use when downloading at scale, hitting 429s or stuck activations, choosing Orders API vs COG reads, or designing a resumable batch Planet pipeline.

1 skill

Build a global PMTiles archive from raster predictions or any large vector dataset on a single fat node. Covers raster→polygon→geoparquet→FlatGeobuf→sharded tippecanoe→tile-join, with profiling, error recovery, and I/O-aware staging. Use when the user asks to vectorize raster predictions, polygonize change layers, build PMTiles at over 100M-feature scale, profile tippecanoe, decide tippecanoe flags, choose between tippecanoe / planetiler / pmtiles merge, or speed up a slow pmtiles build.

1 skill

End-to-end catalog creation from a data source - extract, enrich metadata, generate assets, push to remote

1 skill

Use when publishing, managing, or converting cloud-native geospatial data catalogs with the Portolan CLI. Covers init, add, check, push, pull, sync, partitioning, and format conversion workflows.

1 skill

Generate high-quality thumbnails from Portolan collections using chiitiler (MapLibre GL Native). Renders the collection's actual styles/default.json server-side with optional basemap. Requires Node.js 18+.

1 skill

Use when exploring, querying, analyzing, or visualizing data from a Portolan catalog (STAC-based cloud-native geospatial data). Covers navigating STAC metadata, querying GeoParquet with DuckDB, cross-dataset joins, geospatial analysis, and creating interactive maps with PMTiles/MapLibre/deck.gl/Potree.

1 skill

Register a Portolan catalog in the Portolan registry by opening a pull request that adds a catalog entry file.

1 skill

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

1 skill

Upload geospatial data to Source Cooperative with proper metadata and READMEs using Portolan CLI.

1 skill

This skill should be used when downloading Tessera embeddings with the geotessera CLI. Covers coverage inspection, bbox and region downloads, GeoTIFF vs NPY export, band selection, registry configuration, cache behavior, and local visualization.

1 skill

Build GeoZarr multiscale pyramids (overviews) into existing Zarr stores for tile/web streaming — choosing a resampling operator that respects the data's semantics (probability simplex, categorical, continuous), cascading levels, striping work across batch workers or dask without losing shards, and verifying completeness. Use when adding overviews/pyramids/multiscales to a Zarr or GeoZarr store, downsampling ML prediction rasters, or debugging a pyramid with missing or wrong shards.

1 skill