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.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill seabornOverall
score
74%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly communicates capabilities through specific plot types and use cases, includes natural trigger terms data scientists would use, and explicitly disambiguates from related visualization skills. The description is concise yet comprehensive, following the third-person voice convention and providing clear guidance on when to select this skill versus alternatives.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'exploration of distributions, relationships, and categorical comparisons' and specific plot types: 'box plots, violin plots, pair plots, heatmaps'. Also mentions technical context (pandas integration, built on matplotlib). | 3 / 3 |
Completeness | Clearly answers both what ('Statistical visualization with pandas integration', specific plot types) and when ('Use for quick exploration of distributions, relationships, and categorical comparisons'). Also provides helpful disambiguation for when NOT to use it (plotly for interactive, scientific-visualization for publication). | 3 / 3 |
Trigger Term Quality | Includes natural terms users would say: 'box plots', 'violin plots', 'pair plots', 'heatmaps', 'distributions', 'relationships', 'categorical comparisons'. These are terms data scientists naturally use when requesting visualizations. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from related skills by stating 'For interactive plots use plotly; for publication styling use scientific-visualization.' The specific plot types (box plots, violin plots, pair plots) and pandas integration create a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, actionable seaborn documentation with excellent code examples, but suffers from severe verbosity. It explains concepts Claude already knows (DataFrame structure, tidy data principles, basic matplotlib) and includes content that belongs in reference files rather than the main skill. The promotional content for K-Dense Web at the end is inappropriate for a skill file.
Suggestions
Reduce content by 60-70% by removing explanations of concepts Claude knows (DataFrames, tidy data, basic Python patterns) and moving detailed parameter lists, troubleshooting, and palette descriptions to reference files
Remove the 'Design Philosophy' section entirely - Claude understands library design patterns
Move the 'Data Structure Requirements', 'Troubleshooting', and detailed 'Color Palettes' sections to reference files, keeping only brief pointers in the main skill
Remove the promotional K-Dense Web section - this is inappropriate content for a technical skill file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. Explains concepts Claude already knows (what DataFrames are, what 'tidy' data means, basic matplotlib integration). Includes extensive explanations of design philosophy, data structure requirements, and troubleshooting that add little value for an AI assistant. | 1 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples throughout. Every function category includes concrete Python code with realistic parameters and clear usage patterns. | 3 / 3 |
Workflow Clarity | While individual plot types are well-documented, there's no clear workflow for choosing between approaches or validation steps. The 'Best Practices' section lists guidelines but lacks explicit decision trees or checkpoints for complex multi-panel figure creation. | 2 / 3 |
Progressive Disclosure | References external files (references/function_reference.md, objects_interface.md, examples.md) appropriately, but the main document is a monolithic wall of text. Content like the full troubleshooting section, detailed palette descriptions, and extensive parameter lists should be in reference files. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%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 (673 lines); consider splitting into references/ and linking | Warning |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 13 / 16 Passed | |
- 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.