CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

geopandas

A Python library for reading, writing, and analyzing geospatial vector data; use it when you need spatial operations (buffer/overlay/join), CRS reprojection, or map visualization on formats like Shapefile/GeoJSON/GeoPackage or PostGIS.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/geopandas/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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.

The core technical content (usage triggers, dependencies, executable example, CRS/join/overlay implementation notes) is solid and actionable. However, the second half of the file is generic boilerplate padding, and the reference bundle, while real, is poorly signaled, dragging down efficiency and navigation.

Suggestions

Delete or collapse the generic template sections (When Not to Use, Required Inputs, Recommended Workflow, Deterministic Output Rules, Output Contract, Validation and Safety Rules, Failure Handling, Completion Checklist, Quick Validation, Scope Reminder) — they add ~60% of the body without geopandas-specific content.

Replace the parenthetical reference list with per-topic pointers in the relevant sections, e.g., under CRS rules: 'See references/crs-management.md for EPSG selection guidance', so each reference is clearly signaled where it is needed.

Add a concrete validation checkpoint to the example, such as 'if gdf.crs is None: gdf = gdf.set_crs("EPSG:4326")' before to_crs, to give the workflow a real feedback step.

DimensionReasoningScore

Conciseness

The technical half (When to Use, Key Features, Dependencies, Example Usage, Implementation Details) is lean, but roughly ten trailing sections (When Not to Use, Required Inputs, Recommended Workflow, Deterministic Output Rules, Output Contract, Validation and Safety Rules, Failure Handling, Completion Checklist, Quick Validation, Scope Reminder) are generic template padding that add no geopandas-specific value, and 'Scope Reminder' repeats the description verbatim.

2 / 5

Actionability

The example is complete, runnable code covering read, CRS inspection, reprojection, buffer, plot, and write, and Implementation Details gives real API signatures (sjoin predicate=, sjoin_nearest max_distance=, overlay how=). Minor gaps: pipe-syntax signatures are illustrative rather than literal, no install command, and the boilerplate sections give only vague direction.

4 / 5

Workflow Clarity

The commented 6-step example sequences clearly and reprojecting before metric calculations is a real checkpoint, but there are no validation or feedback loops (e.g., guarding against a missing CRS before to_crs) and 'Recommended Workflow' is abstract boilerplate rather than geopandas-specific steps.

3 / 5

Progressive Disclosure

Six real one-level-deep reference files exist and are named in the body, but they are buried in a single parenthetical list at the end of Key Features with no per-topic signaling or links, and Implementation Details partially duplicates content that belongs in those references.

3 / 5

Total

12

/

20

Passed

Description

87%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 description that clearly states both what the skill covers and when to use it, with concrete operations and format names as triggers. The only deductions are the second-person 'use it when you need' phrasing and the absence of a few natural synonyms like 'GIS'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('reading, writing, and analyzing geospatial vector data', 'buffer/overlay/join', 'CRS reprojection', 'map visualization') plus named formats (Shapefile/GeoJSON/GeoPackage, PostGIS). Base score 5, but 'use it when you need' uses second-person voice, triggering the -1 specificity penalty per the judging guidelines.

4 / 5

Completeness

Explicitly answers both 'what' (a Python library for reading, writing, and analyzing geospatial vector data) and 'when' (use it when you need spatial operations, CRS reprojection, or map visualization) with concrete trigger phrases, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Good natural-keyword coverage: 'spatial operations', 'buffer', 'overlay', 'join', 'CRS reprojection', 'Shapefile', 'GeoJSON', 'GeoPackage', 'PostGIS'. Missing a few natural synonyms and extensions users would say, such as 'GIS' or '.shp'/'.geojson'.

4 / 5

Distinctiveness Conflict Risk

Clear niche: 'geospatial vector data' with vector-specific triggers (buffer/overlay/join, CRS, Shapefile/GeoJSON/GeoPackage, PostGIS) is well-differentiated from adjacent skills such as raster GIS or general data-processing skills; minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Data Analysis/geopandas/SKILL.md

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.