statistical-analysis

Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required sample sizes, or write up results - even if they never name a specific test. Covers t-tests, ANOVA, chi-square, correlation, regression, non-parametric and Bayesian methods. For low-level model APIs, see the statsmodels and pymc skills.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%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 well-structured, highly actionable skill body with executable examples, an explicit assumption-check feedback loop, and clean one-level-deep progressive disclosure to verified bundle files. The only weakness is mild verbosity in a few rhetorical passages and the duplicated 'When to Use' list.

Suggestions

Trim rhetorical padding such as 'Skipping steps is how analyses end up retracted' and 'a p-value says an effect exists; the effect size says whether anyone should care' to tighten token efficiency.

Remove or condense the 'When to Use This Skill' section since it restates the frontmatter description and adds no new trigger information.

Consider moving the version-compatibility notes block into references/ (e.g. assumptions_and_diagnostics.md or a dedicated compatibility note) so the main body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious, version-specific gotchas (ArviZ 89% default, one-sided BF removal, compute_effsize_from_t lacking a CI) and avoids explaining basics Claude already knows, but some rhetorical prose ('Skipping steps is how analyses end up retracted') and a 'When to Use' section that re-states the description could be trimmed.	4 / 5
Actionability	Copy-paste-ready, executable code blocks for t-tests, ANOVA with post-hoc, regression with diagnostics, Bayesian t-test, and a priori/sensitivity power analysis, all with concrete column names and version-aware API usage.	5 / 5
Workflow Clarity	A clear 6-step Analysis Workflow is sequenced in order with an explicit validation checkpoint (assumption checking) and a feedback loop - 'If an assumption fails, switch to the remedial test... and report both the plan and the change' - reinforced by the Statistical Integrity checklist.	5 / 5
Progressive Disclosure	The body is an overview that signals one-level-deep references to all five real reference files and the bundled script, each verified to exist in references/ and scripts/, and a Bundled Resources section enumerates them for easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

100%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, complete description that names concrete capabilities, supplies natural trigger phrases for both what and when, and actively reduces overlap risk by routing low-level model API work to sibling skills. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions (test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, APA-formatted reporting) plus the covered method families, giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what (guided statistical analysis with the listed capabilities) and when ('Use whenever a user wants to compare groups, test a hypothesis...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrasing is well covered - 'compare groups', 'test a hypothesis', 'analyze experimental or survey data', 'compute required sample sizes', 'write up results' - including the hedge 'even if they never name a specific test'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (statistical analysis for research data) with distinct triggers, and it explicitly de-conflicts the only adjacent area by routing low-level model APIs to the statsmodels and pymc skills, keeping conflict risk minimal.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/statistical-analysis/SKILL.md
Commit: 1e5eeff

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.