mirror of
https://github.com/K-Dense-AI/claude-scientific-skills.git
synced 2026-03-27 07:09:27 +08:00
85591617fc
Major improvements to the GeoMaster geospatial science skill: ### New Features - Added Rust geospatial support (GeoRust crates: geo, proj, shapefile, rstar) - Added comprehensive coordinate systems reference documentation - Added troubleshooting guide with common error fixes - Added cloud-native workflows (STAC, Planetary Computer, COG) - Added automatic skill activation configuration ### Reference Documentation - NEW: references/coordinate-systems.md - CRS fundamentals, UTM zones, EPSG codes - NEW: references/troubleshooting.md - Installation fixes, runtime errors, performance tips - UPDATED: references/programming-languages.md - Now covers 8 languages (added Rust) ### Main Skill File - Streamlined SKILL.md from 690 to 362 lines (500-line rule compliance) - Enhanced installation instructions with uv and conda - Added modern cloud-native workflow examples - Added performance optimization tips ### Documentation - NEW: GEOMASTER_IMPROVEMENTS.md - Complete changelog and testing guide - UPDATED: README.md - Highlight new capabilities ### Skill Activation - Created skill-rules.json with 150+ keywords and 50+ intent patterns - Supports file-based and content-based automatic activation The skill now covers 8 programming languages (Python, R, Julia, JavaScript, C++, Java, Go, Rust) with 500+ code examples across 70+ geospatial topics.
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
- core-libraries.md - GDAL, Rasterio, Fiona, Shapely, PyProj, GeoPandas
- remote-sensing.md - Satellite missions, optical/SAR/hyperspectral analysis, image processing
- gis-software.md - QGIS/PyQGIS, ArcGIS/ArcPy, GRASS GIS, SAGA GIS integration
- scientific-domains.md - Marine, atmospheric, hydrology, agriculture, forestry applications
- advanced-gis.md - 3D GIS, spatiotemporal analysis, topology, network analysis
- programming-languages.md - R, Julia, JavaScript, C++, Java, Go geospatial tools
- machine-learning.md - Deep learning for RS, spatial ML, GNNs, XAI for geospatial
- big-data.md - Distributed processing, cloud platforms, GPU acceleration
- industry-applications.md - Urban planning, disaster management, utilities, transportation
- specialized-topics.md - Geostatistics, optimization, ethics, best practices
- data-sources.md - Satellite data catalogs, open data repositories, API access
- 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 for detailed installation instructions.
Core Python Stack
conda install -c conda-forge gdal rasterio fiona shapely pyproj geopandas
Remote Sensing
pip install rsgislib torchgeo earthengine-api
Quick Examples
Calculate NDVI from Sentinel-2
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
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/claude-scientific-skills repository. For contributions, see the main repository guidelines.