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

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

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 that uses executable examples, decision tables, and a one-level-deep reference to keep the overview lean. The main gaps are minor: a trimmable persona intro and a few validation checkpoints whose recovery paths are left implicit.

Suggestions

Trim or remove the opening role-prompt paragraph ('You are an expert statistician...'); Claude does not need to be told it is an expert, and the skill's value is in its tools and decision frameworks, not persona framing.

Add an explicit recovery branch to Mode 2's sanity-check step, e.g., 'If traffic cannot deliver N within the window, raise the MDE or extend the run — do not proceed underpowered.'

For Mode 1's Decide step, make the underpowered-recovery loop explicit ('If n is below required sample size, re-run sample_size_calculator.py and extend before concluding') rather than relying on the Decision Framework's 'Extend' row.

Dimension	Reasoning	Score
Conciseness	Largely efficient — dense tables and executable code blocks carry the content, and theory is correctly offloaded to the reference file — but the opening role-prompt ('You are an expert statistician and data scientist...') and some framing prose are minor over-explanation that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready bash commands with real argument values for all three scripts, covering the common cases (Z-test, t-test, chi-square, proportion/mean sample size, proportion/mean CI), plus a scenario-to-test mapping table.	5 / 5
Workflow Clarity	Three clearly sequenced entry-point modes with checklists (Quality Loop confidence tags, Decision Framework) providing validation, but recovery paths are implicit — e.g., Mode 2's 'Sanity-check' does not state what to do if traffic cannot deliver N.	4 / 5
Progressive Disclosure	Clear sectioned overview with a well-signaled one-level-deep reference (references/statistical-testing-concepts.md, verified to exist) for theory, scripts split into separate files all correctly referenced — operational guidance inline, theory external, easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

95%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, concrete description that names multiple specific capabilities and pairs them with a natural 'Use when' trigger clause covering the three main use cases. Its only weakness is the second-person voice in the trigger clause, which the rubric penalizes.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions ('Run hypothesis tests, analyze A/B experiment results, calculate sample sizes, and interpret statistical significance with effect sizes') — comprehensive coverage matching anchor 5, but reduced by 1 because the trigger clause uses second-person voice ('Use when you need to').	4 / 5
Completeness	Explicitly answers both 'what' (the four actions) 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	Comprehensive natural terms with synonyms — 'hypothesis tests', 'A/B experiment results', 'sample sizes', 'statistical significance', 'effect sizes', 'observed differences are real' — phrases a user would naturally say when invoking this skill.	5 / 5
Distinctiveness Conflict Risk	Clear niche (statistical hypothesis testing / A/B experimentation / sample sizing / effect sizes) with distinct triggers and minimal overlap risk against general data-analysis skills.	5 / 5
	Total	19 / 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: alirezarezvani/claude-skills
Path: engineering/statistical-analyst/skills/statistical-analyst/SKILL.md
Commit: 19392f7

Reviewed: ~2 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.