CtrlK
BlogDocsLog inGet started
Tessl Logo

geopandas

Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.

87

1.35x
Quality

86%

Does it follow best practices?

Impact

87%

1.35x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

92%

8%

Industrial Facility Impact Zone Analysis

CRS projection and geometry analysis

Criteria
Without context
With context

uv package manager

0%

100%

Projected CRS for buffering

100%

100%

Projected CRS for area

100%

100%

UTM or equal-area CRS selection

100%

100%

preserve_topology in simplify

100%

100%

Use .copy() for geometry modification

100%

100%

Geometry validation

0%

0%

GeoPackage output format

100%

100%

Multiple named layers

100%

100%

Area in square meters

100%

100%

100%

31%

Delivery Zone Assignment and Nearest Depot Routing

Spatial joins and multi-source data integration

Criteria
Without context
With context

uv package manager

0%

100%

CRS alignment before sjoin

50%

100%

sjoin predicate used

100%

100%

sjoin_nearest with max_distance

0%

100%

distance_col in sjoin_nearest

50%

100%

Merge on GeoDataFrame

100%

100%

GeoPackage output

100%

100%

Named layer

100%

100%

Projected CRS for distance

100%

100%

Output is GeoDataFrame

100%

100%

70%

31%

Regional Economic Inequality Mapping

Choropleth mapping with classification and interactive maps

Criteria
Without context
With context

uv package manager

0%

100%

Arrow write

0%

0%

Arrow read

0%

0%

Filter during read

100%

100%

Classification scheme

33%

100%

Legend on static map

62%

100%

Interactive map via explore()

0%

100%

Interactive map saved as HTML

100%

100%

GeoPackage format

100%

100%

pyarrow installed

0%

0%

Repository
K-Dense-AI/claude-scientific-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.