agentsclimarketplace

Geospatial data loading

Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3-flash-preview/earthquake-plate-calculation/geospatial-data-loading

Techniques for loading and initial processing of GeoJSON and coordinate-based datasets using GeoPandas.From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill geospatial-data-loading

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

SKILL.md

1.2 KB, 302 tokens by cl100k_base, as published. Nobody here has run it

Geospatial Data Loading

Overview

GeoPandas is the primary library for loading geographic data in Python. It extends pandas to allow spatial operations on geometric types.

Loading GeoJSON

GeoJSON is a standard format for geographic data.

import geopandas as gpd

# Load directly from file
gdf = gpd.read_file("data.json")

# Inspect CRS (Coordinate Reference System)
print(gdf.crs) # Usually EPSG:4326 for GeoJSON

Creating GDF from Dictionary/List

If you have raw JSON or a list of dictionaries with coordinates:

from shapely.geometry import Point
import geopandas as gpd

data = [
    {"id": "eq1", "lat": 10.5, "lon": 120.3},
    {"id": "eq2", "lat": -5.2, "lon": -150.8}
]

geometry = [Point(d["lon"], d["lat"]) for d in data]
gdf = gpd.GeoDataFrame(data, geometry=geometry, crs="EPSG:4326")

Handling Multi-Geometries

Some datasets might contain MultiPolygon or MultiLineString. GeoPandas handles these automatically, but you might want to "explode" them into individual parts:

gdf_exploded = gdf.explode(index_parts=False)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.