geospatial-data-discovery
Skill0 starsChanged 23 days agoMITView on GitHub
Discover, evaluate, and acquire open and authoritative geospatial data (vector boundaries, raster imagery, satellite/Earth observation, DEM elevation, land cover, buildings, street networks, and climate grids). Use when searching for GIS datasets, satellite imagery (Sentinel, Landsat), OpenStreetMap/Overture layers, STAC catalogs, national open-data portals, or Cloud-Optimized GeoTIFFs (COG) and GeoParquet distributions.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- jaakla/openmapstacktheir own version, first seen Sep 28, 2026
- jaakla/openmapstack-skillstheir own version, first seen Sep 28, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- jaakla/openmapstack★ 76same name
- jaakla/openmapstack-skills★ 76same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accuracy-assessmentSkill
- brainstormingSkill
- crs-and-unitsSkill
- design-postgis-tablesSkill
- gdalSkill
- geomasterSkill
- geopandasSkill
- geoparquet-validationSkill
- geospatial-frontendSkill
- geozarrSkill
- networkxSkill
- raster-processingSkill
- sar-basicsSkill
- satellite-preprocessingSkill
- scientific-visualizationSkill
- spectral-indicesSkill
- stac-and-cloud-accessSkill
- statistical-analysisSkill
- systematic-debuggingSkill
- time-series-and-changeSkill
- vector-qualitySkill
- verificationSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Use this skill when:
- Distinctive: line 26
Before downloading or integrating any spatial dataset, verify:
- Distinctive: line 36
License & Attribution: Verify specific attribution requirements (e.g., "Contains modified Copernicus Sentinel data [year]", "© …
- Distinctive: line 37
Data Freshness & Provenance: Verify update cadence, release version, and authoritative producing agency.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Geospatial Data Discovery & Verification
Domain-specific methodology for identifying, evaluating, and obtaining geospatial and Earth observation datasets with spatial precision, format compatibility, and attribution integrity.
When to Use
Use this skill when:
- Sourcing geographic boundaries, admin polygons, roads, or building footprints
- Locating satellite imagery (Copernicus Sentinel-2, USGS Landsat, MODIS, NAIP)
- Finding elevation/DEM rasters (SRTM, Copernicus DEM, 3DEP)
- Querying SpatioTemporal Asset Catalogs (STAC) or cloud-native buckets
- Checking data licenses (ODbL, CC-BY, Public Domain) before ingestion
10-Point Geospatial Evaluation Checklist
Before downloading or integrating any spatial dataset, verify:
- Area of Interest (AOI): Does the bounding box or polygon strictly cover the study area?
- Temporal Window: What are the acquisition date ranges, baseline years, or repeat cycle frequencies?
- Spatial Resolution / Scale: Ground Sample Distance (e.g. 10m Sentinel vs 30m Landsat vs sub-meter aerial) or vector scale ratio (1:10k vs 1:110m).
- Coordinate Reference System (CRS): Is the native CRS geographic (WGS84 / EPSG:4326) or a local projected system (e.g., UTM zone, State Plane)?
- Data Geometry / Type: Vector (Point/Line/Polygon), Raster (single/multi-band), Point Cloud (LiDAR), or Mesh.
- Cloud Cover & Quality Mask: For optical Earth observation, check cloud percentage threshold and QA band availability.
- Distribution Format: Cloud-native (COG, GeoParquet, PMTiles, GeoZarr) vs legacy archive (Shapefile, raw HDF, zipped GeoTIFF).
- Catalog & API Access: STAC API endpoint, S3/GCS bucket requester-pays status, WFS/WMS endpoint, or direct bulk download.
- License & Attribution: Verify specific attribution requirements (e.g., "Contains modified Copernicus Sentinel data [year]", "© OpenStreetMap contributors").
- Data Freshness & Provenance: Verify update cadence, release version, and authoritative producing agency.
Recommended Authoritative Data Sources
- OpenStreetMap (OSM) / Geofabrik: Global crowd-sourced vector data (roads, POIs, land use). License: ODbL.
- Overture Maps Foundation: Cloud-native GeoParquet releases of buildings, places, transportation, and base layers. License: CDLA-Permissive-2.0 / ODbL.
- USGS EarthExplorer / Landsat: 30m multispectral global archive (Landsat 8/9). Public Domain.
- Copernicus Open Access / Sentinel Hub: 10m multispectral (Sentinel-2), SAR (Sentinel-1). Open access with attribution.
- NASA Earthdata / Planetary Computer / AWS Open Data: Curated STAC catalogs offering direct COG/Zarr streaming.
- Natural Earth: Public domain global vector and raster map dataset at 1:10m, 1:50m, and 1:110m scales.
- Copernicus DEM (GLO-30) / SRTM: 30m global digital elevation models.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.