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.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is geopandas in K-Dense-AI/scientific-agent-skills

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, actionable skill body that leverages progressive disclosure effectively through six real reference files. Its main weakness is workflow clarity: the batch and file-output workflows lack the validation/verification checkpoints the rubric expects for destructive or batch operations.

Suggestions

Add explicit validation checkpoints to the workflows — e.g. assert `gdf.is_valid.all()` before spatial operations and verify output files were written before declaring success — so the 'Load, Transform, Analyze, Export' and join workflows include verification steps.

Include a validate→fix→retry feedback loop for batch/output operations like `to_file()`, `sjoin()`, and `overlay()` to satisfy the rubric's expectation of feedback loops for destructive or batch operations.

Remove the duplicate 'Detailed Documentation' reference list (the same links already appear inline in each section) and trim the introductory paragraph explaining what GeoPandas is, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable code, but the opening line explaining what GeoPandas is and the 'Detailed Documentation' section that duplicates links already shown inline are minor over-explanation that could be trimmed.	4 / 5
Actionability	It provides concrete, executable API calls for the common cases (read_file, to_crs, buffer, sjoin, overlay, dissolve, plot, explore), but the workflow examples reference undefined variables (points_gdf, roads, engine) leaving minor gaps.	4 / 5
Workflow Clarity	The 'Load, Transform, Analyze, Export' and join workflows have clear numbered sequences, but they include batch/output operations (to_file, sjoin, overlay) with no validation or verification checkpoints, capping this dimension at 3.	3 / 5
Progressive Disclosure	The body is a concise overview with six clearly signaled one-level-deep references (data-structures.md, data-io.md, crs-management.md, geometric-operations.md, spatial-analysis.md, visualization.md), all of which exist in ./references/, with easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states what GeoPandas does and when to use it, with extensive concrete action coverage and natural trigger terms. The only gaps are the absence of explicit file extensions and minor overlap with generic mapping skills.

Dimension	Reasoning	Score
Specificity	The description lists numerous concrete actions — 'buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats' — giving comprehensive coverage of capabilities rather than vague language.	5 / 5
Completeness	It explicitly answers 'what' ('Python library for working with geospatial vector data including...') and 'when' with two concrete trigger clauses — 'Use when working with geographic data...' and 'Use for tasks like buffer analysis...'.	5 / 5
Trigger Term Quality	Strong natural keyword coverage ('shapefiles, GeoJSON, GeoPackage', 'spatial analysis', 'choropleth mapping', 'spatial joins') with synonyms, but it omits explicit file extensions like .shp and .gpkg that the top anchor rewards.	4 / 5
Distinctiveness Conflict Risk	The geospatial-vector-data framing carves a clear niche with distinct triggers, but 'creating maps' and 'integration with matplotlib/folium/cartopy' create minor overlap risk with general visualization skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/data-engineering/geopandas/SKILL.md
Commit: fcd2e11

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.