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

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

75%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.

A thorough, highly actionable seaborn reference with copy-paste code across all major plot types and well-organized sections plus properly signaled reference files. The main weakness is conciseness: the body inlines a good deal of API detail Claude already knows that could live in the reference files.

Suggestions

Trim or relocate the full color-palette enumerations and per-parameter explanations of hue/size/style into references/function_reference.md to reduce body length and token cost.

Consolidate the repeated 'When to use' bullet lists across sections into a single decision table to avoid restating the same guidance.

Move the per-category 'Key parameters' blocks into the function reference, keeping only a representative example inline in the body.

Dimension	Reasoning	Score
Conciseness	The body is well-structured and mostly useful, but at ~660 lines it restates seaborn API knowledge Claude already has (full palette enumerations, per-parameter explanations of hue/size/style, multiple 'When to use' lists) that could be tightened or pushed to references. It is not a 2 because the material is organized and actionable rather than padded tutorial prose, and not a 4 because the unnecessary explanatory restatement is more than minor.	3 / 5
Actionability	Provides abundant copy-paste-ready, executable code across every major plot category, with concrete function names and key parameter listings covering the common cases. It is not below 5 because the examples are complete and runnable, matching the anchor-5 example.	5 / 5
Workflow Clarity	The 'Best Practices' section sequences guidance from data prep through plot choice, faceting, semantic mapping, estimation, matplotlib integration, and saving, giving a clear sequence. It is not a 5 because there are no explicit validation/feedback checkpoints, and not a 3 because the sequence is clear and the skill is non-destructive so the validation cap does not apply.	4 / 5
Progressive Disclosure	A Resources section clearly signals three one-level-deep reference files (function_reference.md, objects_interface.md, examples.md), all confirmed present, with a concise overview pointing to them. It is not a 5 because substantial reference-grade content (full palette and per-category parameter lists) is inlined in the body rather than fully delegated to the reference files.	4 / 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.

A strong, third-person description that cleanly answers both 'what' and 'when' with concrete plot-type triggers and explicit boundaries against adjacent skills. Minor gaps in trigger-term synonyms are the only thing keeping specificity and trigger_term_quality from full marks.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities—'distributions, relationships, and categorical comparisons', named plot types (box plots, violin plots, pair plots, heatmaps), and pandas integration—rather than vague language, though it is domain-and-use-case framing more than an exhaustive action list. It is not a 5 because the actions are described as use cases rather than a comprehensive enumeration of operations.	4 / 5
Completeness	Explicitly states both what it does ('Statistical visualization with pandas integration... attractive defaults... Built on matplotlib') and when to use it ('Use for quick exploration of distributions, relationships, and categorical comparisons'), with concrete trigger phrases matching the anchor-5 example. Not below 5 because both 'what' and 'when' are clearly and concretely present.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('distributions', 'relationships', 'box plots', 'violin plots', 'heatmaps') plus redirect triggers ('interactive plots use plotly', 'publication styling use scientific-visualization'). Good coverage, but a few common synonyms (e.g., 'scatter', 'correlation', 'bars') are absent, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (statistical visualization on matplotlib) and actively disambiguates from related skills via explicit redirects to plotly and scientific-visualization, minimizing wrong-skill triggers. The redirects sharpen rather than blur boundaries, so it is not a 4.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (677 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/visualization/seaborn/SKILL.md
Commit: 1d182e9

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.