Geomaster
Ship geospatial or Earth-observation features with GDAL, GeoPandas, remote sensing, and GIS workflows without hunting scattered library docs.
Overview
GeoMaster is an agent skill for the Build phase that delivers geospatial science procedures, library references, and multi-language examples for GIS and remote sensing development.
Install
npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill geomasterWhat is this skill?
- 70+ topical sections spanning remote sensing, GIS platforms, spatial ML, and cloud big-data patterns
- 500+ code examples across seven languages with 300+ geospatial libraries indexed
- Reference tracks for GDAL/Rasterio/GeoPandas plus QGIS, GRASS, and ArcPy integration paths
- Workflows for marine, hydrology, agriculture, disaster, and urban planning domains
- 70+ sections on geospatial science topics
- 500+ code examples across 7 programming languages
- 300+ geospatial libraries and tools referenced
Adoption & trust: 524 installs on skills.sh; 27.6k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent keeps guessing GDAL, raster, and ontology-heavy GIS APIs because general coding skills lack Earth-observation depth.
Who is it for?
Indie developers building map backends, EO classifiers, or spatial analytics APIs who need curated library and workflow coverage.
Skip if: Builders who only need a single static Mapbox embed with no raster or vector processing on the server.
When should I use this skill?
Implementing GIS, remote sensing, spatial statistics, or ML pipelines for Earth observation and need structured library and workflow guidance.
What do I get? / Deliverables
Implementation plans and code follow documented GeoMaster patterns across libraries, domains, and scalable processing options.
- Geospatial processing scripts or notebooks aligned to reference workflows
- Library and platform choices documented for the target domain
Recommended Skills
Journey fit
Primary shelf is Build because the skill is a large implementation reference for geospatial code, libraries, and pipelines—not ideation or ops tuning. Backend subphase fits data processing, raster/vector operations, and scientific compute that power maps and models behind the product.
How it compares
Domain encyclopedia for geospatial build work, not a lightweight one-shot map UI generator skill.
Common Questions / FAQ
Who is geomaster for?
Solo and indie builders shipping GIS, remote sensing, or spatial ML features who want agent guidance grounded in real library ecosystems.
When should I use geomaster?
During Build when designing pipelines, choosing stacks (GDAL vs desktop GIS), or implementing domain-specific EO or hydrology workflows.
Is geomaster safe to install?
It is documentation-heavy; review the Security Audits panel on this page and treat downloaded geodata and cloud credentials as sensitive in your environment.
SKILL.md
READMESKILL.md - Geomaster
# GeoMaster Geospatial Science Skill ## Overview GeoMaster is a comprehensive geospatial science skill covering: - **70+ sections** on geospatial science topics - **500+ code examples** across 7 programming languages - **300+ geospatial libraries** and tools - Remote sensing, GIS, spatial statistics, ML/AI for Earth observation ## Contents ### Main Documentation - **SKILL.md** - Main skill documentation with installation, quick start, core concepts, common operations, and workflows ### Reference Documentation 1. **core-libraries.md** - GDAL, Rasterio, Fiona, Shapely, PyProj, GeoPandas 2. **remote-sensing.md** - Satellite missions, optical/SAR/hyperspectral analysis, image processing 3. **gis-software.md** - QGIS/PyQGIS, ArcGIS/ArcPy, GRASS GIS, SAGA GIS integration 4. **scientific-domains.md** - Marine, atmospheric, hydrology, agriculture, forestry applications 5. **advanced-gis.md** - 3D GIS, spatiotemporal analysis, topology, network analysis 6. **programming-languages.md** - R, Julia, JavaScript, C++, Java, Go geospatial tools 7. **machine-learning.md** - Deep learning for RS, spatial ML, GNNs, XAI for geospatial 8. **big-data.md** - Distributed processing, cloud platforms, GPU acceleration 9. **industry-applications.md** - Urban planning, disaster management, utilities, transportation 10. **specialized-topics.md** - Geostatistics, optimization, ethics, best practices 11. **data-sources.md** - Satellite data catalogs, open data repositories, API access 12. **code-examples.md** - 500+ code examples across 7 programming languages ## Key Topics Covered ### Remote Sensing - Sentinel-1/2/3, Landsat, MODIS, Planet, Maxar - SAR, hyperspectral, LiDAR, thermal imaging - Spectral indices, classification, change detection ### GIS Operations - Vector data (points, lines, polygons) - Raster data processing - Coordinate reference systems - Spatial analysis and statistics ### Machine Learning - Random Forest, SVM, CNN, U-Net - Spatial statistics, geostatistics - Graph neural networks - Explainable AI ### Programming Languages - **Python** - GDAL, Rasterio, GeoPandas, TorchGeo, RSGISLib - **R** - sf, terra, raster, stars - **Julia** - ArchGDAL, GeoStats.jl - **JavaScript** - Turf.js, Leaflet - **C++** - GDAL C++ API - **Java** - GeoTools - **Go** - Simple Features Go ## Installation See [SKILL.md](SKILL.md) for detailed installation instructions. ### Core Python Stack ```bash conda install -c conda-forge gdal rasterio fiona shapely pyproj geopandas ``` ### Remote Sensing ```bash pip install rsgislib torchgeo earthengine-api ``` ## Quick Examples ### Calculate NDVI from Sentinel-2 ```python import rasterio import numpy as np with rasterio.open('sentinel2.tif') as src: red = src.read(4) nir = src.read(8) ndvi = (nir - red) / (nir + red + 1e-8) ``` ### Spatial Analysis with GeoPandas ```python import geopandas as gpd zones = gpd.read_file('zones.geojson') points = gpd.read_file('points.geojson') joined = gpd.sjoin(points, zones, predicate='within') ``` ## License MIT License ## Author K-Dense Inc. ## Contributing This skill is part of the K-Dense-AI/scientific-agent-skills repository. For contributions, see the main repository guidelines. # Advanced GIS Topics Advanced spatial analysis techniques: 3D GIS, spatiotemporal analysis, topology, and network analysis. ## 3D GIS ### 3D Vector Operations ```python import geopandas as gpd from shapely.geometry import Point, LineString, Polygon import pyproj import numpy as np # Create 3D geometries (with Z coordinate) point_3d = Point(0, 0, 100) # x, y, elevation line_3d = LineString([(0, 0, 0), (100, 100, 50)]) # Load 3D data gdf_3d = gpd.read_file('buildings_3d.geojson') # Access Z coordinates gdf_3d['height'] = gdf_3d.geometry.apply(lambda g: g.coords[0][2] if g.has_z else None) # 3D buffer (cylinder) def buffer_3d(point, ra