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.
82
71%
Does it follow best practices?
Impact
90%
2.81xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/seaborn/SKILL.mdQuality
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 concisely covers specific capabilities, natural trigger terms, clear usage guidance, and explicit boundaries with related skills. The inclusion of when to use alternative skills (plotly, scientific-visualization) is particularly effective for disambiguation. It uses proper third-person voice throughout and avoids vague language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and plot types: 'exploration of distributions, relationships, and categorical comparisons' plus explicit chart types like 'box plots, violin plots, pair plots, heatmaps'. Also mentions pandas integration and matplotlib foundation. | 3 / 3 |
Completeness | Clearly answers 'what' (statistical visualization with pandas integration, specific plot types) and 'when' ('Use for quick exploration of distributions, relationships, and categorical comparisons'). Also includes explicit boundary guidance on when NOT to use it ('For interactive plots use plotly; for publication styling use scientific-visualization'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'box plots', 'violin plots', 'pair plots', 'heatmaps', 'distributions', 'relationships', 'categorical comparisons', 'pandas', 'matplotlib'. These are terms data scientists and analysts naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit differentiation from related skills: distinguishes itself from plotly (interactive) and scientific-visualization (publication styling). The specific plot types and 'pandas integration' with 'attractive defaults' clearly identify this as a seaborn-style skill with a well-defined niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive and highly actionable with excellent executable code examples, but it is far too verbose for a SKILL.md file. It reads like a complete seaborn tutorial/documentation page rather than a concise skill reference, explaining many concepts Claude already knows (data structures, design philosophy, what various plot types are for). The content that should live in the referenced files (function_reference.md, examples.md) is largely duplicated inline, defeating the purpose of progressive disclosure.
Suggestions
Reduce the SKILL.md to ~100-150 lines covering quick start, a concise plot type selection guide (table format), key gotchas, and clear pointers to reference files for detailed parameters and examples.
Move the detailed per-category function listings, parameter descriptions, and extensive code examples into the referenced files (function_reference.md, objects_interface.md, examples.md) and actually provide those bundle files.
Remove sections that explain concepts Claude already knows: 'Design Philosophy', 'Data Structure Requirements' (long vs wide form), and explanatory text like 'Understanding this distinction is crucial for effective seaborn usage'.
Consolidate the 'Choose the Right Plot Type' best practice into a compact decision table at the top of the skill, replacing the verbose per-category sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is extremely verbose at ~500+ lines. It explains concepts Claude already knows well (what long-form vs wide-form data is, what a DataFrame is, design philosophy of seaborn, when to use each interface). Sections like 'Design Philosophy', 'Data Structure Requirements', and extensive explanations of figure-level vs axes-level functions are unnecessary padding. Much of this reads like a tutorial rather than a concise skill reference. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout every section. Function signatures, key parameters, and concrete usage patterns are all present and specific. | 3 / 3 |
Workflow Clarity | For a visualization library skill, there aren't destructive multi-step workflows, but the 'Common Patterns' and 'Best Practices' sections provide reasonable sequencing. However, there are no validation checkpoints (e.g., checking if data is in the right format before plotting, verifying output). The troubleshooting section helps but is reactive rather than preventive. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with everything inlined. It references `references/function_reference.md`, `references/objects_interface.md`, and `references/examples.md` at the bottom, but no bundle files are provided, and the vast majority of content that should be in those reference files (detailed parameter listings, extensive examples for every plot type, color palette catalogs) is duplicated inline. The SKILL.md should be a concise overview pointing to these references. | 1 / 3 |
Total | 7 / 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 — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (672 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
cbcae7b
- 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.