Name: statistical-analyst
Rating: 68.8 (1 reviews)
Author: alirezarezvani

statistical-analyst

Run hypothesis tests, analyze A/B experiment results, calculate sample sizes, and interpret statistical significance with effect sizes. Use when you need to validate whether observed differences are real, size an experiment correctly before launch, or interpret test results with confidence.

Quality

83%

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

The canonical home for this skill is statistical-analyst in alirezarezvani/claude-skills

Quality

Content

78%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 body is highly actionable with executable code and clear multi-mode workflows, and it is largely concise. Its main weakness is progressive disclosure: all referenced scripts and the reference document are absent from the bundle, leaving dangling links.

Suggestions

Ship the referenced bundle files (the three scripts under scripts/ and references/statistical-testing-concepts.md) or remove the references and inline the essential content.

Move the effect-size interpretation tables (Cohen's d/h, Cramér's V) into references/statistical-testing-concepts.md since they restate standard thresholds Claude already knows.

Add an explicit validate→fix→retry checkpoint in the analysis modes (e.g., re-check test assumptions before reporting) to strengthen workflow validation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable examples and compact tables, but inline effect-size interpretation tables (Cohen's d/h/Cramér's V thresholds) and explanations of concepts like Simpson's paradox and peeking are material Claude already knows and could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready commands for all three scripts with realistic arguments, flags, and JSON output options, plus a test-selection table and decision framework covering the common cases.	5 / 5
Workflow Clarity	Three clearly sequenced modes (Clarify→Choose→Run→Interpret→Decide; Define→Calculate→Sanity-check→Document) with a Quality Loop confidence tagging checkpoint, but validation is somewhat implicit rather than explicit validate→fix→retry loops.	4 / 5
Progressive Disclosure	Sections are well-organized and mostly inline-appropriate, but every referenced bundle path — scripts/hypothesis_tester.py, sample_size_calculator.py, confidence_interval.py, and references/statistical-testing-concepts.md — points to files that do not exist, breaking navigation.	3 / 5
	Total	16 / 20 Passed

Description

88%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.

The description is strong: it states concrete capabilities and provides explicit, natural-language trigger conditions in third person. It is comprehensive on the 'what' and 'when' with only minor gaps in keyword synonyms and slight overlap risk with adjacent analytics skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Run hypothesis tests, analyze A/B experiment results, calculate sample sizes, and interpret statistical significance with effect sizes' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (run tests, analyze results, size experiments, interpret significance) and when ('Use when you need to validate whether observed differences are real, size an experiment correctly before launch, or interpret test results with confidence') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keywords ('A/B experiment results', 'statistical significance', 'sample sizes', 'effect sizes') that users would say, but a few common variations like 'confidence interval', 'p-value', and 'power' are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche around statistical testing and significance with distinct triggers, but 'analyze A/B experiment results' creates minor overlap risk with related product/campaign analytics skills noted in the body.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 16 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/statistical-analyst/SKILL.md
Commit: 19392f7

Reviewed: ~4 hours 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.