geopandas

Guidance and local audit tools for Python workflows that directly use GeoPandas GeoSeries, GeoDataFrame, spatial operations, or vector-data I/O.

Quality

85%

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

Quality

Content

100%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 content is an exemplar of a dense, actionable skill body: executable code and commands, an explicit validation-gated workflow, and clean one-level-deep progressive disclosure to real reference files. No meaningful weaknesses across the four dimensions.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — it states non-obvious facts (axis order, antimeridian wrapping, GeoParquet schema semantics, removed APIs) with no padding or explanation of basics, and version/date details are confined to the migration/sources sections where they belong.	5 / 5
Actionability	It provides copy-paste-ready executable guidance — pinned 'uv pip install' commands, a runnable CRS-check Python snippet, exact CLI invocations with full arguments, and named API methods with precise semantics — covering the common cases comprehensively.	5 / 5
Workflow Clarity	The 8-step 'Correctness gates' checklist is explicitly sequenced with validation checkpoints (count null/invalid/collapsed, validate before and after repair, audit cardinality, reopen and compare counts/types), and destructive/batch operations are guarded with explicit feedback loops.	5 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with details split across six real reference files, each linked one level deep via inline 'See [X](references/X.md)' markers and consolidated in a reference index, making navigation easy.	5 / 5
	Total	20 / 20 Passed

Description

70%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.

The description is specific and clearly niche-scoped to GeoPandas vector workflows, but it lacks an explicit 'Use when...' trigger clause, leaving the 'when to use' only weakly implied. Adding a concrete usage trigger and a few more natural synonyms/file extensions would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger scenarios, e.g. 'Use when working with GeoDataFrames, spatial joins, CRS reprojection, or GeoParquet/GeoPackage I/O.'

Include common natural synonyms and file extensions users say — 'shapefile', '.gpkg', 'GeoParquet', '.parquet' — to broaden trigger-term coverage.

Lead with concrete verbs (audit, reproject, validate, join) instead of the abstract 'Guidance and local audit tools' to strengthen specificity.

Dimension	Reasoning	Score
Specificity	Names concrete GeoPandas entities and capability areas — 'GeoSeries, GeoDataFrame, spatial operations, or vector-data I/O' plus 'local audit tools' and 'Guidance' — giving several specific actions/targets with only minor coverage gaps, fitting between the 3 and 5 anchors.	4 / 5
Completeness	It has a clear 'what' (guidance and audit tools for workflows using these objects/operations) but no explicit 'Use when...' trigger clause, so 'when' is only weakly implied, which caps completeness at 3 per the rubric guidance.	3 / 5
Trigger Term Quality	Includes natural terms users would say — 'Python workflows', 'GeoPandas', 'GeoSeries', 'GeoDataFrame', 'spatial operations', 'vector-data I/O' — but omits common synonyms/extensions like .gpkg, GeoParquet, or shapefile, so it is good but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to GeoPandas with named library, object types, and operations, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/geopandas/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.