CtrlK
BlogDocsLog inGet started
Tessl Logo

statistical-and-uncertainty-visualization

Design statistically honest and uncertainty-aware visualizations. Use when the user needs help showing distributions, intervals, confidence, missingness, sampling effects, or analytical rigor in charts and dashboards.

65

Quality

77%

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/build-web-data-visualization/skills/statistical-and-uncertainty-visualization/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-structured overview that trusts Claude's knowledge and points cleanly to real one-level-deep references. It is held back by abstract rather than concrete guidance and by two broken shared-theory reference links.

Suggestions

Add one or two concrete encoding recipes to the body (e.g., 'Use error bands / 95% intervals for estimation uncertainty; annotate sample size as n=; show missingness as a distinct visual state rather than encoding it as zero') so the SKILL.md is actionable without opening references.

Fix or remove the two broken shared-theory references (../../references/foundations/task-abstraction-and-chart-selection.md and perception-color-and-encoding.md) so every referenced path resolves in the bundle.

Add an explicit verification checkpoint to the Working Pattern, e.g., a final step that confirms the chosen encoding preserves the variation/uncertainty that matters to the decision before finalizing the view.

DimensionReasoningScore

Conciseness

The body is lean (~45 lines) and assumes Claude's competence — it never explains what distributions, confidence intervals, or box plots are, and every section is directive rather than padded. Minor thematic repetition of "show variation honestly" is too slight to drop below the lean/efficient anchor.

3 / 3

Actionability

Guidance is directive ("Choose encodings that show spread, uncertainty, missingness, or sample size honestly", "Avoid summarizing away the variation") but abstract; the body gives no concrete encoding recipes (e.g., use error bands for CIs, annotate n=), deferring specifics to references.

2 / 3

Workflow Clarity

The Working Pattern is a clear, logical 4-step sequence and Output Expectations serve as a partial checklist, but there are no explicit validation checkpoints or feedback loops; checkpoints are implicit rather than stated, fitting the "sequence present but checkpoints missing" anchor.

2 / 3

Progressive Disclosure

The body is a well-organized overview with one-level-deep, clearly grouped references (all four skill references verified to exist), but two of the six referenced paths ("../../references/foundations/task-abstraction-and-chart-selection.md" and "perception-color-and-encoding.md") do not resolve to any file, leaving dead links that impair navigation.

2 / 3

Total

9

/

12

Passed

Description

90%Weight 40%Scale 1-3

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, well-structured description that clearly states both the capability and an explicit trigger condition with natural user terms. Its only mild weakness is that it states one core action rather than enumerating several distinct concrete operations.

DimensionReasoningScore

Specificity

It names a concrete action ("Design statistically honest and uncertainty-aware visualizations") and a clear domain, but the list "distributions, intervals, confidence, missingness, sampling effects, or analytical rigor" enumerates data concepts/topics rather than multiple distinct concrete operations like the anchor-3 example (extract/fill/merge).

2 / 3

Completeness

It explicitly answers both what ("Design statistically honest and uncertainty-aware visualizations") and when ("Use when the user needs help showing...") with an explicit "Use when" trigger clause.

3 / 3

Trigger Term Quality

Good coverage of natural terms users would actually say — "distributions, intervals, confidence, missingness, sampling effects... in charts and dashboards" — well beyond a single keyword and avoiding generic jargon.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche (statistical honesty and uncertainty) with distinct triggers (missingness, sampling effects, analytical rigor, confidence) that are unlikely to be the primary trigger for a generic chart-selection skill.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.