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

93%

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

86%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: executable code throughout, a clear assumption-checked workflow with feedback loops, and clean progressive disclosure to real reference files. The only weakness is minor verbosity in a few prose passages that could be tightened.

Suggestions

Tighten the 'Statistical Integrity' and 'Bayesian Statistics' prose sections to bullet-point essentials to lift conciseness toward the lean 5 anchor.

Add an explicit post-test validation/retry checkpoint in the workflow (e.g., 'if convergence diagnostics fail, re-sample with more tune/draws and re-check') to push workflow_clarity to 5.

Move the library version-compatibility notes into a dedicated 'Compatibility / known pitfalls' subsection header so they are scannable rather than woven into the Installation narrative.

Dimension	Reasoning	Score
Conciseness	Efficient and assumes Claude's competence; the version-compatibility notes earn their place because they flag real, specific pitfalls (renamed pingouin columns, ArviZ 89% defaults, dropped one-sided BF). Minor instances of prose that could be trimmed keep it just below the lean 5 anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready code blocks for t-test, ANOVA, regression, Bayesian t-test, effect sizes, and power analysis, each with specific gotchas (Welch correction, k_groups vs n-per-group, ci_prob=0.95) covering the common cases.	5 / 5
Workflow Clarity	Clear 6-step analysis sequence with an explicit assumption-check validation checkpoint and a feedback loop ('If an assumption fails, switch to the remedial test and report both the plan and the change'). A 5 would require more granular per-step validation and explicit retry loops for the batch/destructive-adjacent operations.	4 / 5
Progressive Disclosure	Clear overview with well-signaled, one-level-deep references that all resolve to real bundle files (references/*.md, scripts/assumption_checks.py), and content appropriately split between SKILL.md and the reference files, matching the 5 anchor.	5 / 5
	Total	18 / 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.

An exemplary description that concisely states concrete capabilities, provides natural trigger phrases a user would actually say, explicitly covers both what and when, and disambiguates from adjacent skills. It is third-person, specific, and free of fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting' — with comprehensive coverage of the domain, matching the 5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (the listed analysis capabilities) and 'when' via the 'Use whenever a user wants to...' clause with concrete trigger phrases, matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say — 'compare groups, test a hypothesis, analyze experimental or survey data, compute required sample sizes, or write up results' — including synonyms and the 'even if they never name a specific test' guidance.	5 / 5
Distinctiveness Conflict Risk	Clear niche (guided end-to-end statistical analysis) with distinct triggers, and explicit disambiguation ('For low-level model APIs, see the statsmodels and pymc skills') minimizes conflict risk.	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: b2a92ba

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.