mcpField
A
ab-test-analysis

ab-test-analysis

github.com/phurynData & databases27.5k2.9k installsUpdated 2w ago
Repository

About ab-test-analysis

ab-test-analysis is a skill for evaluating A/B tests and turning results into product decisions. It checks experiment quality, calculates statistical measures, reviews guardrails, and recommends a next step.

Key features

  1. 01Validates sample size, duration, and randomization
  2. 02Calculates lift, p-values, and confidence intervals
  3. 03Checks guardrail metrics
  4. 04Maps results to product recommendations
  5. 05Analyzes provided raw data with Python

Use cases

  1. 01Deciding whether to ship an experiment variant
  2. 02Investigating a winning metric with guardrail declines
  3. 03Assessing an underpowered or inconclusive test

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/phuryn/pm-skills --skill ab-test-analysis

After installing, type/ab-test-analysisin Claude Code to confirm it loaded.

Details

From the project README

A/B Test Analysis

Evaluate A/B test results with statistical rigor and translate findings into clear product decisions.

Context

You are analyzing A/B test results for $ARGUMENTS.

If the user provides data files (CSV, Excel, or analytics exports), read and analyze them directly. Generate Python scripts for statistical calculations when needed.

Instructions

  1. Understand the experiment:

    • What was the hypothesis?
    • What was changed (the variant)?
    • What is the primary metric? Any guardrail metrics?
    • How long did the test run?
    • What is the traffic split?

  2. Validate the test setup:

    • Sample size: Is the sample large enough for the expected effect size?
      • Use the formula: n = (Z²α/2 × 2 × p × (1-p)) / MDE²
      • Flag if the test is underpowered (<80% power)
    • Duration: Did the test run for at least 1-2 full business cycles?
    • Randomization: Any evidence of sample ratio mismatch (SRM)?
    • Novelty/primacy effects: Was there enough time to wash out initial behavior changes?

  3. Calculate statistical significance:

    • Conversion rate for control and variant
    • Relative lift: (variant - control) / control × 100
    • p-value: Using a two-tailed z-test or chi-squared test
    • Confidence interval: 95% CI for the difference
    • Statistical significance: Is p < 0.05?
    • Practical significance: Is the lift meaningful for the business?

    If the user provides raw data, generate and run a Python script to calculate these.

  4. Check guardrail metrics:

    • Did any guardrail metrics (revenue, engagement, page load time) degrade?
    • A winning primary metric with degraded guardrails may not be a true win

  5. Interpret results:

    OutcomeRecommendation
    Significant positive lift, no guardrail issuesShip it — roll out to 100%
    Significant positive lift, guardrail concernsInvestigate — understand trade-offs before shipping
    Not significant, positive trendExtend the test — need more data or larger effect
    Not significant, flatStop the test — no meaningful difference detected
    Significant negative liftDon't ship — revert to control, analyze why

  6. Provide the analysis summary:

    ## A/B Test Results: [Test Name]

**Hypothesis**: [What we expected]
**Duration**: [X days] | **Sample**: [N control / M variant]

| Metric | Control | Variant | Lift | p-value | Significant? |
|---|---|---|---|---|---|
| [Primary] | X% | Y% | +Z% | 0.0X | Yes/No |
| [Guardrail] | ... | ... | ... | ... | ... |

**Recommendation**: [Ship / Extend / Stop / Investigate]
**Reasoning**: [Why]
**Next steps**: [What to do]

Think step by step. Save as markdown. Generate Python scripts for calculations if raw data is provided.

Further Reading

Comments

Markdown supported