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.
85
82%
Does it follow best practices?
Impact
87%
1.35xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that thoroughly covers specific capabilities, provides rich natural trigger terms, and clearly delineates both what the skill does and when to use it. The geospatial domain is well-defined with distinct terminology that minimizes conflict risk. The description uses proper third-person voice throughout and avoids vague language or buzzwords.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: buffer analysis, spatial joins, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, converting between spatial file formats, overlay operations, choropleth mapping. | 3 / 3 |
Completeness | Clearly answers both 'what' (Python library for geospatial vector data with specific operations listed) and 'when' (explicit 'Use when working with geographic data for...' and 'Use for tasks like...' clauses with detailed trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: shapefiles, GeoJSON, GeoPackage, geographic data, spatial analysis, spatial joins, choropleth, coordinate transformations, PostGIS, matplotlib, folium, cartopy, buffer analysis, reprojecting, and specific file format mentions. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on geospatial vector data with specific triggers like shapefiles, GeoJSON, GeoPackage, PostGIS, spatial joins, and coordinate transformations that are unlikely to conflict with non-geospatial skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, well-structured GeoPandas skill with excellent actionability — nearly every concept is backed by executable code. Its main weaknesses are the absence of validation checkpoints in workflows (especially important for spatial operations where CRS mismatches or invalid geometries can silently corrupt results) and the missing bundle files that the progressive disclosure structure depends on. Some minor verbosity could be trimmed by removing explanations of concepts Claude already knows.
Suggestions
Add explicit validation checkpoints to workflows, e.g., check `gdf.geometry.is_valid.all()` after loading data, verify CRS matches before joins with an assertion, and validate output row counts after spatial joins.
Provide the referenced bundle files (references/data-structures.md, references/spatial-analysis.md, etc.) or remove the references to avoid broken links.
Trim explanatory text that Claude already knows — remove the opening sentence defining GeoPandas, the bullet definitions of GeoSeries/GeoDataFrame, and obvious best practices like 'use .copy() when modifying geometry columns.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good code examples, but includes some unnecessary explanations Claude would already know (e.g., 'GeoPandas extends pandas to enable spatial operations on geometric types', listing what GeoSeries/GeoDataFrame are, explaining what buffer/simplify/centroid do). The optional dependencies section and performance tips are useful but could be tighter. The best practices section has some obvious items like 'always check CRS before spatial operations.' | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples throughout — reading files, reprojecting, spatial joins, overlay operations, visualization, and complete multi-step workflows. Commands for installation are specific. Code snippets cover the most common use cases with real function signatures and parameters. | 3 / 3 |
Workflow Clarity | The 'Load, Transform, Analyze, Export' and 'Spatial Join and Aggregate' workflows are clearly sequenced, but they lack validation checkpoints. There's no explicit step to validate geometries (despite mentioning `.is_valid` in best practices), no error handling for CRS mismatches, and no feedback loops for catching issues in multi-step spatial operations. For operations like spatial joins and overlays that can silently produce incorrect results, validation steps are important. | 2 / 3 |
Progressive Disclosure | The skill references six detailed documents in a `references/` directory with clear navigation links, which is excellent structure. However, no bundle files are provided, meaning all those references are broken/non-existent. The main file also includes substantial inline content that overlaps with what the reference files would cover, making the split somewhat redundant. The detailed documentation index section is well-organized though. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
cbcae7b
- Reviewed
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.