CtrlK
BlogDocsLog inGet started
Tessl Logo

seaborn

Seaborn is a Python visualization library for creating publication-quality statistical graphics. Use this skill for dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures with minimal code.

61

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/seaborn/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 extensive executable examples, held back by verbosity and weak progressive disclosure: it inlines a large API reference that belongs in separate files and cites references/*.md files that are not present in the bundle.

Suggestions

Move the bulk function/parameter catalogs, color palette listings, and theming details into the referenced files under references/ (and actually ship those files), keeping SKILL.md a concise overview with quick-start and decision guidance.

Trim explanatory prose Claude already knows — the Design Philosophy section, the long-form vs wide-form tidy-data tutorial, and filler sentences like 'Understanding this distinction is crucial for effective seaborn usage'.

Add a short explicit end-to-end workflow (load/prepare data → choose plot type via the decision matrix → create → customize/save) so the workflow_clarity dimension reflects a real sequenced process.

DimensionReasoningScore

Conciseness

The ~660-line body is mostly actionable API reference (function lists, parameters, code) but carries unnecessary explanatory prose Claude already knows — the Design Philosophy bullets restating Seaborn's nature, the long-form/wide-form tidy-data explainer, and filler like 'Understanding this distinction is crucial for effective seaborn usage' — so it is efficient in places but could be tightened and offloaded.

3 / 5

Actionability

It provides fully executable, copy-paste-ready code across relational, distribution, categorical, regression, matrix, and grid plot families with specific function names and key parameters, covering the common cases comprehensively; the few undefined placeholder variables (timeseries, data) are minor and consistent with the anchor 5 example.

5 / 5

Workflow Clarity

Content is well organized by plot category and includes a 'Choose the Right Plot Type' decision matrix and recipe-style Common Patterns, but there is no explicit sequenced multi-step workflow with checkpoints; this is acceptable for a non-destructive reference skill yet only moderately satisfies the workflow-sequencing anchor.

3 / 5

Progressive Disclosure

Section structure is clear and a Resources section signals three reference files with descriptions, but the bulk API reference (function catalogs, parameter tables, palette and theming listings) is inlined in SKILL.md rather than split out, and the referenced references/*.md files do not actually exist on disk, matching the anchor where content that should be separate is inline and references are only partially realized.

3 / 5

Total

14

/

20

Passed

Description

83%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 clearly states what Seaborn does and gives an explicit 'Use this skill for' trigger clause covering several concrete scenarios. It is held back only by slightly abstract capability phrasing and minor overlap with general plotting skills.

DimensionReasoningScore

Specificity

Names the domain and several concrete capabilities — 'publication-quality statistical graphics', 'dataset-oriented plotting', 'multivariate analysis', 'automatic statistical estimation', 'complex multi-panel figures' — but a couple are use-case noun phrases rather than verb-led actions, leaving minor abstraction short of the fully comprehensive anchor 5.

4 / 5

Completeness

It explicitly answers 'what' ('a Python visualization library for creating publication-quality statistical graphics') and 'when' via the concrete trigger clause 'Use this skill for dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures', matching the anchor that requires both with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good keyword coverage with natural terms a data user would say ('statistical graphics', 'multivariate analysis', 'multi-panel figures', 'dataset-oriented plotting'), but it omits common synonyms and concrete plot names (heatmap, violin plot, seaborn) that users frequently invoke, so it falls short of anchor 5.

4 / 5

Distinctiveness Conflict Risk

It names Seaborn explicitly and carves a statistical-graphics niche, but 'Python visualization library' and general plotting triggers overlap with closely related matplotlib/dataviz skills, so it is mostly distinct with minor overlap risk rather than minimal.

4 / 5

Total

17

/

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (673 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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.