seaborn

Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/seaborn/SKILL.md

Quality

Content

71%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 well-structured with strong progressive disclosure and mostly actionable code, but it carries several padded sections explaining basic seaborn/pandas concepts Claude already knows. Trimming the Design Philosophy and elementary best-practice commentary would lift conciseness without losing value.

Suggestions

Trim or remove the 'Design Philosophy' section and the 'Data Preparation' best practice that explains well-structured DataFrames — these restate seaborn/pandas basics Claude already knows.

Replace abstract placeholder variables in code examples (x='x', y='y', hue='category') with concrete values tied to a named dataset so snippets are copy-paste runnable end-to-end.

Condense the 'Best Practices' list by merging redundant plot-type selection guidance already implied by the reference files, keeping only version-specific or non-obvious advice inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with code and bullets, but several sections over-explain concepts Claude already knows (Design Philosophy, basic 'Choose the Right Plot Type' and 'well-structured DataFrames' guidance), landing it at 'mostly efficient with some unnecessary explanation'.	3 / 5
Actionability	Provides mostly executable, concrete code across Quick Start, objects interface, statistical estimation, and figure saving, but several examples use abstract placeholder variables (x='x', hue='category') rather than runnable data, leaving minor gaps.	4 / 5
Workflow Clarity	Numbered Best Practices (1-7) and a plot-type decision table give a clear loose sequence with interface-selection guidance; no destructive/batch operations so the validation cap does not apply, though it is reference-oriented rather than a strict workflow.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview with seven one-level-deep reference files (all referenced paths resolve to real files in ./references/), clearly signaled and described in the 'Plotting Functions, Grids, Palettes, and Patterns' section, with content appropriately split.	5 / 5
	Total	16 / 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.

The description is strong: it states concrete capabilities, gives clear 'use when' triggers with specific plot-type keywords, and explicitly disambiguates from adjacent skills. Minor gaps in action/synonym coverage keep specificity and trigger-term quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('quick exploration of distributions, relationships, and categorical comparisons') plus specific plot types ('box plots, violin plots, pair plots, heatmaps'), with only minor coverage gaps; not a fully comprehensive action list so it stops below 5.	4 / 5
Completeness	Explicitly answers both what ('Statistical visualization with pandas integration... Best for box plots, violin plots, pair plots, heatmaps') and when ('Use for quick exploration...'), with concrete trigger phrases and explicit boundary guidance against plotly and scientific-visualization.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('box plots, violin plots, pair plots, heatmaps', 'distributions, relationships, categorical comparisons') but misses some common synonyms and variations, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Has a clear statistical-visualization niche and explicit disambiguation ('For interactive plots use plotly; for publication styling use scientific-visualization'), giving minimal conflict risk.	5 / 5
	Total	18 / 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/seaborn/SKILL.md
Commit: 9cf7d9a

Reviewed: 5 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.