Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

GeoMaster – Geospatial Science Toolkit

An all-in-one geospatial skill covering satellite imagery, GIS operations, spatial statistics, and Earth observation ML.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

GeoMaster gives Claude Code battle-tested workflows and code patterns for geospatial data.

  • Remote sensing: Sentinel-2, Landsat, MODIS, SAR and hyperspectral processing plus NDVI/EVI/SAVI/NDWI indices
  • Vector & raster ops: GeoPandas spatial joins, buffers, overlays; Rasterio windowed read/write
  • CRS guardrails: when to use EPSG:4326 vs 3857 vs UTM, estimate_utm_crs(), forced projected CRS for area/distance
  • Terrain & network analysis: slope, aspect, hillshade from DEMs; OSMnx + NetworkX routing
  • Spatial ML: Random Forest image classification, references for torchgeo and deep learning
  • Cloud-native: STAC search, Planetary Computer, COG read/write/validation, xarray + dask at scale
  • 8 languages (Python, R, Julia, JS, C++, Java, Go, Rust), 13 reference docs, 500+ code examples

Who it's for

  • Researchers and grad students tracking vegetation, water or land-cover change from satellite data
  • GIS practitioners moving from manual QGIS clicks to reproducible Python scripts
  • Urban planning, disaster response, agriculture, forestry and marine analysts
  • Data engineers migrating to STAC/COG cloud-native pipelines

Example uses

  1. "Pull a 2020–2023 Sentinel-2 NDVI time series for this coordinate and plot it" → Earth Engine collection filtering, <20% cloud filter, NDVI band, DataFrame export
  2. "Join monitoring points to admin polygons and compute per-zone mean and std dev" → CRS check, then sjoin + groupby aggregation code
  3. "From this DEM, mask areas steeper than 25° and build a landslide risk map" → terrain metrics, masking, and saving as a valid Cloud-Optimized GeoTIFF

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/geomaster folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/geomaster/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/geomaster ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create the skills folder if needed: mkdir -p ~/.claude/skills
  3. Copy the skill in: cp -r scientific-agent-skills/skills/geomaster ~/.claude/skills/
  4. Verify the references/ subfolder came along: ls ~/.claude/skills/geomaster
  5. Install the core stack — conda (or miniforge) is strongly recommended for GDAL: conda install -c conda-forge gdal rasterio fiona shapely pyproj geopandas
  6. Add only what you need, e.g. cloud workflows: pip install pystac-client planetary-computer odc-stac xarray rioxarray; network analysis: pip install osmnx networkx folium
  7. For Google Earth Engine, run pip install earthengine-api then earthengine authenticate and set your project ID.
  8. Restart Claude Code and ask a geospatial question (e.g. "compute NDVI from this GeoTIFF") — the skill triggers automatically.
View source on GitHub ↗License: MIT