メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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".
Attach a DuckDB database for persistent querying. Use when the user has a .duckdb file they want to explore, or when they want to persist query results across sessions. Explores schema and wires up state.sql so all DuckDB skills can access it.
Search DuckDB and DuckLake documentation via full-text search. Use when encountering DuckDB errors, looking up function syntax, or when other skills hit unknown DuckDB behavior. Also use proactively when unsure about DuckDB features.
Install or update DuckDB extensions. Use when DuckDB reports a missing extension, when the user asks to install/update extensions, or when other skills delegate here. Each argument is a plain extension name or name@repo. Pass --update to update.
Run SQL queries against DuckDB databases or ad-hoc files. Accepts raw SQL or natural language. Use whenever the user wants to query data, explore tables, run analytics, or ask questions about datasets — even if they don't say "DuckDB" explicitly.
Read and explore any data file (CSV, JSON, Parquet, Avro, Excel, spatial, remote) using DuckDB. Use proactively when the user mentions a data file, asks "what's in this file", or wants to explore/preview/describe any dataset — even without saying DuckDB.
| name | gdal |
| description | 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. |
| allowed-tools | Bash, Read, Glob, Grep |
Run via pixi run gdal. Always use the unified CLI, NOT legacy tools.
gdal <FILE> → gdal info <FILE>gdal read <FILE> ! ... → gdal pipeline <FILE> ! ...gdal info <dataset> — metadata for any dataset (raster or vector)gdal convert <in> <out> — auto-detect raster/vector conversiongdal pipeline <steps> — chain steps with ! separatorgdal vector ...)vector info <dataset> — schema, layers, features, CRS, extentvector check-geometry <dataset> — find invalid geometriesvector check-coverage <dataset> — validate polygon coveragevector convert <in> <out> — format conversion (no CRS change)vector reproject <in> <out> -d EPSG:xxxx — reproject (-d/--dst-crs, required)
-s/--src-crs to override source CRSvector clip <in> <out> --bbox xmin ymin xmax ymax or --geometry clip.gpkgvector buffer <in> <out> --distance <m>vector simplify <in> <out> --tolerance <val>vector filter <in> <out> --where "<SQL>"vector sql <in> <out> --statement "<SQL>"vector make-valid <in> <out>vector make-point <in> <out> --x-col lon --y-col latvector explode-collections <in> <out>vector set-geom-type <in> <out> --type POLYGONvector segmentize <in> <out> --max-length <val>vector swap-xy <in> <out>vector concat <in1> <in2> ... <out>vector layer-algebra <in1> <in2> <out> --operation union|intersection|difference|symdifferencevector simplify-coverage <in> <out>vector clean-coverage <in> <out>vector select <in> <out> --fields "f1,f2"vector set-field-type <in> <out> --field name --type Integervector edit <in> --metadata KEY=VALUEvector partition <in> <out_dir> --field <col>vector index <inputs...> <out>vector rasterize <in> <out> --resolution <res>vector grid <in> <out> --algorithm invdistpixi run gdal vector pipeline \
read input.gpkg \
! reproject --dst-crs EPSG:4326 \
! filter --where "pop > 10000" \
! write output.parquet
gdal raster ...)raster info <dataset> — bands, resolution, CRS, statsraster pixel-info <dataset> --coord <x> <y>raster compare <r1> <r2>raster convert <in> <out> — format conversionraster reproject <in> <out> --dst-crs EPSG:xxxxraster clip <in> <out> --bbox xmin ymin xmax ymax or --geometry mask.gpkgraster resize <in> <out> --size <w> <h>raster mosaic <inputs...> <out>raster hillshade|slope|aspect|roughness|tpi|tri <in> <out>raster contour <in> <out> --interval <val> — vector outputraster viewshed <in> <out> --coord <x> <y>raster select <in> <out> --bands 1,3raster stack <in1> <in2> <out>raster calc <inputs...> <out> --expression "<formula>"raster scale <in> <out> --src-min 0 --src-max 255raster set-type <in> <out> --type Float32raster unscale <in> <out>raster fill-nodata|nodata-to-alpha|sieve|clean-collar|pansharpen|blend|proximity <in> <out>raster neighbors <in> <out> --mode average --size 3raster reclassify <in> <out> --mapping "0-10:1,10-20:2"raster zonal-stats <raster> <zones> <out>raster polygonize|as-features|footprint <in> <out>raster overview add|delete|refresh <in>raster create <out> --size <w> <h> --bands <n>raster edit <in> --metadata KEY=VALUEraster index|tile <inputs...> <out>pixi run gdal raster pipeline \
read input.tif \
! reproject --dst-crs EPSG:3857 \
! write output.cog.tif --creation-option COMPRESS=DEFLATE
gdal mdim info|convert|mosaic — NetCDF/HDF5/Zarrgdal dataset identify|copy|rename|delete — dataset managementgdal vsi list|copy|delete|move|sync|sozip — virtual filesystem (S3, Azure, GCS, HTTP, ZIP)gdal driver gpkg repack|gti create|openfilegdb repack — driver-specific--config KEY=VALUE, -f FORMAT, --co KEY=VALUE, --lco KEY=VALUE--overwrite, --append, --quiet