Run2 geospatial analysis

Skill cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-flash-lite-preview/earthquake-plate-calculation/run2_geospatial-analysis

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Install

npx -y skills add cxcscmu/SkillLearnBench --skill run2_geospatial-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Geospatial data analysis with geopandas for distance calculations, filtering, and modern API usage.

SKILL.md

1.0 KB, 230 tokens by cl100k_base, as published. Nobody here has run it

Geospatial Analysis with GeoPandas (Improved)

Key Concepts

Coordinate Systems: EPSG:4326 for storage, EPSG:4087 (metric) for distance.
Modern API: As of GeoPandas 1.0+, use unary_union (or union_all() for newer versions) to combine geometries.
Data Conversion: When using raw GeoJSON, extract properties and geometry.coordinates manually before GeoDataFrame creation.

Updated Pattern

import geopandas as gpd
from shapely.geometry import Point

# 1. Load data
# 2. Extract components if necessary
# 3. Project to metric CRS
METRIC_CRS = "EPSG:4087"
points_proj = gdf.to_crs(METRIC_CRS)
# 4. Combine geometries using .union_all()
boundary_geom = boundary_gdf.to_crs(METRIC_CRS).geometry.union_all()
# 5. Calculate distance
gdf["dist"] = points_proj.geometry.distance(boundary_geom)

What ships with it

Read from the repository