ai-data-registry

Validate project environment health. Use before running pipelines, after setup, or when tools fail unexpectedly. Checks pixi, DuckDB, GDAL, gpio, extensions, state.sql, and cross-tool compatibility.

GeoParquet optimization via gpio CLI (geoparquet-io). Use when creating, inspecting, validating, sorting, partitioning, or enriching GeoParquet files — even if the user just says "optimize this parquet" or "add spatial index". Covers Hilbert sorting, compression, bbox covering, STAC metadata, and cloud upload.

DuckDB v1.5 spatial/GIS analytics with ST_*, H3, A5, and S2/geography extensions. Use for SQL queries, file exploration, spatial analysis, discrete global grids, GeoParquet, ArcGIS REST, DuckLake, session state, docs search, or extension management, even without saying "DuckDB".

Build data processing pipelines using DuckDB, GDAL, and gpio as pixi tasks. Use when creating ETL workflows, multi-step data transformations, format conversions, or batch processing — even if the user just says "process this data" or "build a pipeline".

Geospatial data processing with the unified GDAL CLI (3.12+). Use when converting, inspecting, reprojecting, or processing raster/vector data — even if the user just says "convert this shapefile" or "what CRS is this file". Replaces legacy ogr2ogr/gdalinfo/ogrinfo.