CtrlK
BlogDocsLog inGet started
Tessl Logo

seaborn

Statistical visualization library integrated with pandas; use it when you need fast EDA of distributions, relationships, and categorical comparisons (e.g., box/violin/pair plots and heatmaps) with strong default aesthetics on top of matplotlib.

56

Quality

71%

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 ./scientific-skills/Data Analysis/seaborn/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 core seaborn content — usage triggers, executable tri-example code, and parameter-level implementation notes — is high quality, but it is buried under ~90 lines of generic validation/output boilerplate that is irrelevant to a plotting library. Worse, the three bundled reference files are never referenced from the body, so the skill's progressive-disclosure structure is effectively invisible to a reader.

Suggestions

Delete the generic boilerplate sections (Required Inputs, Recommended Workflow, Deterministic Output Rules, Output Contract, Validation and Safety Rules, Failure Handling, Completion Checklist, Quick Validation, Scope Reminder) — they are template filler with no seaborn-specific content and roughly double the token cost.

Add explicit links to the existing bundle files where they add depth, e.g. under Implementation Details: 'Full function reference: references/function_reference.md; more worked examples: references/examples.md; declarative seaborn.objects interface: references/objects_interface.md'.

Remove the misleading output contract (seaborn_result.md, PASS/FAIL validation summary) — a visualization skill's deliverable is a plot, and this pseudo-workflow conflicts with the actual Example Usage guidance.

DimensionReasoningScore

Conciseness

The seaborn-specific half (When to Use, Key Features, Example Usage, Implementation Details) is tight and useful, but roughly half the body is generic template boilerplate with no seaborn relevance: "A clearly specified task goal aligned with the documented scope", "Return a structured deliverable that is directly usable without reformatting", "Keep output safe, reproducible, and within the documented scope at all times". Several padded sections that earn no tokens place this at anchor 2 rather than the mostly-efficient anchor 3.

2 / 5

Actionability

The Example Usage section is fully executable, copy-paste-ready code covering the three main use cases (semantic scatterplot, faceted catplot, correlation heatmap), and Implementation Details names concrete parameters (`estimator=`, `errorbar=`, `bw_adjust=`, `bins=`, `multiple=`). It falls short of anchor 5 only because surrounding sections like "Select the documented execution path and prefer the simplest supported command" are vague filler rather than executable guidance.

4 / 5

Workflow Clarity

The real usage path (When to Use → Example → Implementation Details) is unambiguous for a simple library skill, but the "Recommended Workflow" and "Output Contract" sections describe an inapplicable file-deliverable process ("seaborn_result.md", "Validation summary: PASS/FAIL") that misleads rather than sequences anything. No destructive or batch operations are involved, so no hard cap applies, but the contradictory pseudo-workflow leaves sequence clarity at anchor 3.

3 / 5

Progressive Disclosure

Three substantial bundle files exist (references/examples.md, references/function_reference.md, references/objects_interface.md — including a whole seaborn.objects guide) yet the body never mentions or links any of them, and API-detail content that belongs in them is instead inlined in Implementation Details. References that exist but are completely unsignaled match anchor 2 ('references are buried' / content that belongs in separate files is inlined), not anchor 3's 'references present but not clearly signaled'.

2 / 5

Total

11

/

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 description: it clearly states both what the skill is and when to use it, with concrete, natural trigger terms a user would actually say. The main gap is that capabilities are presented as a noun catalog rather than an action list, and a few common synonyms (scatter, chart, correlation) are absent.

DimensionReasoningScore

Specificity

The description names concrete capabilities and plot types ("fast EDA of distributions, relationships, and categorical comparisons (e.g., box/violin/pair plots and heatmaps)"), but the catalog is noun-led rather than a comprehensive verb-led action list; it omits common actions like scatter/regression plots and faceting, so it fits 'several specific actions; minor gaps' rather than the comprehensive anchor 5, and is clearly above anchor 3.

4 / 5

Completeness

Explicitly answers both: what ("Statistical visualization library integrated with pandas... on top of matplotlib") and when ("use it when you need fast EDA of distributions, relationships, and categorical comparisons"), with concrete trigger phrases in the 'when' clause — a direct match for anchor 5 and clearly above anchor 4's weaker 'when'.

5 / 5

Trigger Term Quality

Good natural keyword coverage: users would say "EDA", "distributions", "box/violin/pair plots", "heatmaps", "pandas", all present. A few natural terms are missing ("scatter plot", "chart", "correlation matrix"), which matches anchor 4 rather than the comprehensive-synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The seaborn niche (statistical EDA plots, pandas integration, specific plot families) is mostly distinct, but explicit framing "on top of matplotlib" plus generic "statistical visualization" creates minor overlap risk with a matplotlib or generic plotting skill — anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-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.