geopandas

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

Quality

81%

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

92%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 body is a lean, expert-level overview with strong progressive disclosure, explicit validation checkpoints, and copy-paste CLI commands. The main gap is that several core-API sections convey rules as prose rather than runnable examples, which keeps actionability just below the top band.

Suggestions

Add small executable code snippets to the prose-only core-API sections (e.g., a minimal sjoin/overlay example with predicate and an audit of unmatched rows) to push actionability to 5.

Consider moving the full pinned dependency snapshot into a short referenced file while keeping a one-line summary inline, to further tighten the reproducible-environment section.

Cross-link the bundled CLI table entries to the relevant correctness gates so the validation workflow maps directly to the tool that performs each check.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence, with no padding explaining what GeoPandas or basic GIS concepts are; every section earns its place, and the pinned versions/dates serve reproducibility rather than filler, matching the lean-and-efficient anchor.	5 / 5
Actionability	Provides copy-paste-ready bash commands for every bundled CLI, a pinned `uv pip install` block, and an executable CRS python snippet, but several core-API sections (data structures, joins, I/O) are decision rules in prose without accompanying runnable code, leaving minor gaps.	4 / 5
Workflow Clarity	The 8-step numbered "Correctness gates" and the "Output contract" (use a new path, reopen the artifact, compare counts/types) form an explicit sequenced checklist with validation checkpoints and feedback loops (validate before/after repair), matching the top anchor.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with six well-signaled one-level-deep references ("See [CRS management](references/crs-management.md)" etc.), a bundled-CLI table with purposes, and a reference index; the referenced files are real and content is appropriately split, matching the clear-overview anchor.	5 / 5
	Total	19 / 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 distinctive, naming concrete GeoPandas targets and natural trigger terms, but it omits an explicit "Use when..." trigger clause, leaving the "when" only weakly implied and capping completeness. Adding a concrete use-when clause would lift it into the top band.

Suggestions

Append an explicit trigger clause, e.g. "Use when working with GeoPandas GeoSeries/GeoDataFrame, performing spatial joins or overlays, or doing vector-data I/O."

Replace generic action words ("Guidance", "audit tools") with a few concrete verbs (e.g., "audit CRS and geometry validity, plan reprojections and exports") to push specificity toward 5.

Add common synonyms/extensions users might say (e.g., "GeoPackage", "GeoParquet", ".gpkg", ".geoparquet") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the GeoPandas domain and several concrete targets ("GeoSeries, GeoDataFrame, spatial operations, or vector-data I/O") plus "local audit tools", but the action verbs ("Guidance", "audit tools") are slightly generic rather than enumerating distinct operations, so it sits just below a 5.	4 / 5
Completeness	It clearly states what the skill provides ("Guidance and local audit tools for Python workflows that directly use GeoPandas ..."), but there is no explicit "Use when..." trigger clause; the "when" is only weakly implied by the relative clause, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ("GeoPandas", "GeoDataFrame", "spatial operations", "vector-data I/O", "Python workflows") with good coverage, but lacks common synonyms or file extensions, keeping it below a 5.	4 / 5
Distinctiveness Conflict Risk	The description carves out a clear, narrow niche (GeoPandas GeoSeries/GeoDataFrame/spatial operations/vector-data I/O) with distinct triggers and minimal overlap risk with 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: 9cf7d9a

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.