CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

The body is highly actionable with extensive runnable code and clear decision guidance for choosing plot types, and it points cleanly to three substantive one-level-deep reference files. Its main weakness is redundancy: a sizable per-category function reference and long palette/style enumerations are inlined in SKILL.md despite dedicated bundle files covering the same ground.

Suggestions

Trim the 'Plotting Functions by Category' section to one representative example per category (or just the function names) and defer the full parameter listings to references/function_reference.md, which already promises 'comprehensive listing of all seaborn functions with parameters and examples'.

Condense the 'Color Palettes' and 'Theming and Aesthetics' sections to the few palettes/styles that matter for decision-making and move the full enumerations into a reference file, keeping the body under its current ~660 lines.

Remove explanations of concepts Claude already knows, such as the long-form vs wide-form data tutorial framing ('Each variable is a column, each observation is a row'), and keep only the seaborn-specific conversion idiom (df.melt).

DimensionReasoningScore

Conciseness

The body is mostly efficient cheat-sheet material, but it inlines a ~150-line per-category function listing that duplicates references/function_reference.md's stated purpose, and includes explanations Claude already knows (e.g., "Each variable is a column, each observation is a row") plus full enumerations of palettes, styles, and contexts that could be trimmed or moved.

3 / 5

Actionability

Fully executable, copy-paste-ready snippets cover the common cases throughout — e.g. sns.scatterplot with semantic mappings, sns.heatmap(corr, annot=True, fmt='.2f', center=0), faceting via relplot, and g.savefig('figure.pdf', dpi=300, bbox_inches='tight') — with concrete parameter listings per function category.

5 / 5

Workflow Clarity

For a reference-style skill with no multi-step or destructive operations, decision guidance is clear ('When to use' blocks, the 'Choose the Right Plot Type' data-shape mapping, and issue-to-fix Troubleshooting entries), but there is no explicit end-to-end sequence with checkpoints, matching 'clear sequence with most checkpoints' rather than the full validation-loop anchor.

4 / 5

Progressive Disclosure

The Resources section lists all three real reference files with descriptions and 'Load reference files as needed', and the references are one level deep (verified no nested references), but the inlined function-by-category and palette detail overlaps the reference files — a minor placement gap against the 'content appropriately split' anchor.

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 description: it states concrete capabilities, gives an explicit 'Use for...' trigger clause with concrete plot-type keywords, and actively routes overlapping use cases (interactivity, publication styling) to other skills. The only weakness is modest keyword breadth (no scatter/correlation/regression terms).

DimensionReasoningScore

Specificity

Names several concrete capabilities ("exploration of distributions, relationships, and categorical comparisons", "box plots, violin plots, pair plots, heatmaps", "pandas integration") with only minor gaps (regression plots, clustermaps, theming are absent), matching the 'several specific actions; minor gaps in coverage' anchor.

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 of distributions, relationships, and categorical comparisons") with concrete trigger phrases, plus explicit routing away ("For interactive plots use plotly; for publication styling use scientific-visualization").

5 / 5

Trigger Term Quality

Good natural keyword coverage ("distributions", "box plots", "violin plots", "heatmaps", "categorical comparisons") that users would actually say, but a few common terms like "scatter plot", "correlation", and "regression" are missing, so it falls short of the comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers and minimal conflict risk: it proactively disambiguates from the nearest competing skills ("Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization").

5 / 5

Total

18

/

20

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (683 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

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.