Greenmamba29/a-b-test-analyzer
.agents/skills/a-b-test-analyzer/SKILL.md
Analyze A/B test results with statistical rigor. Calculates significance, confidence intervals, sample size requirements, and business impact. Generates clear winner declarations and actionable recommendations.
development
Updated Apr 17, 2026
$ install --global
skillsauthnpx skillsauth add Greenmamba29/skillsdotmd_web a-b-test-analyzerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 9:02 PM1.9s1 file scanned
SKILL.md
- name:
- a-b-test-analyzer
- description:
- Analyze A/B test results with statistical rigor. Calculates significance, confidence intervals, sample size requirements, and business impact. Generates clear winner declarations and actionable recommendations.
- license:
- MIT
- tags:
- [analytics, experimentation, ab-testing, statistics, optimization]
A/B Test Analyzer
Overview
Rigorously analyze A/B test experiments using statistical methods to determine winners, validate significance, calculate business impact, and generate clear, decision-ready reports for product and growth teams.
When to Use
- Evaluating the results of a pricing page test (variant A vs B)
- Analyzing email subject line A/B tests for open rate lift
- Determining if a product feature change improved conversion rates
- Checking if enough traffic was collected to reach statistical significance
- Presenting experiment results to stakeholders with clear business impact
Instructions
- Accept inputs: control data (impressions, conversions, revenue), variant data, confidence level (default 95%), primary metric, secondary metrics.
- Validate minimum sample size: calculate required sample size based on baseline conversion rate, MDE (minimum detectable effect), and confidence level.
- Perform statistical significance test:
- For conversion rates: two-proportion z-test.
- For revenue/continuous metrics: Welch's t-test.
- For count data: chi-squared test.
- Calculate: p-value, confidence interval for the difference, observed lift (%), relative lift (%).
- Check for statistical significance at the configured confidence level.
- Segment analysis: break down results by device, geography, user segment if data provided.
- Calculate business impact: projected annual revenue lift based on current traffic and conversion rates.
- Return decision: Winner (control/variant/no winner), statistical summary, business impact, and next steps recommendation.
Environment
CONFIDENCE_LEVEL=0.95
MINIMUM_DETECTABLE_EFFECT=0.05
TEST_TYPE=two_tailed
SEGMENTATION=true
OUTPUT_FORMAT=report|json
Examples
Input:
control:
visitors: 12450
conversions: 498
revenue: 24900
variant:
visitors: 12380
conversions: 559
revenue: 30745
primary_metric: conversion_rate
confidence_level: 0.95
Output:
A/B Test Analysis Report
Winner: VARIANT (statistically significant)
Control CR: 4.00% | Variant CR: 4.51%
Relative lift: +12.8%
p-value: 0.0031 (significant at 95% CI)
Confidence interval: [+0.21%, +1.01%]
Revenue per visitor: Control $2.00 vs Variant $2.48
Projected annual impact: +$562,000 (based on current traffic)
Recommendation: Ship variant to 100% of traffic
Related Skills
Greenmamba29/customer-onboarder
tools
VerifiedTrustedCommunity
Automate end-to-end new customer onboarding for SaaS and marketplace platforms. Use when onboarding new customers after signup or contract signing, including account provisioning in CRM (HubSpot/Salesforce), sending personalized welcome email sequences via SendGrid, creating and tracking onboarding checklists, scheduling kickoff calls via Calendly/Cal.com, monitoring customer health scores, and generating time-to-value reports. Triggers on tasks involving new customer setup, onboarding automation, welcome sequences, CSM task assignment, or onboarding health tracking.
SKILL.mdUpdated Apr 17, 2026
Greenmamba29/zapier-migrator
development
VerifiedTrustedCommunity
Migrates Zapier zaps to Make.com scenarios automatically. Use when asked to convert, port, or recreate Zapier workflows in Make.com.
SKILL.mdUpdated Apr 17, 2026
Greenmamba29/webhook-orchestrator
development
VerifiedTrustedCommunity
Routes, transforms and fans out webhook payloads across multiple services. Use when you need to receive an incoming webhook and dispatch it to multiple downstream endpoints with payload transformation.
SKILL.mdUpdated Apr 17, 2026
Greenmamba29/.agents/skills/webapp-testing
tools
VerifiedTrustedCommunity
| name | description | license | tags | |------|-------------|---------|------| | webapp-testing | Generate and execute comprehensive test suites for web applications. Covers unit, integration, E2E, and visual regression tests. Analyzes application structure to create meaningful test cases with high coverage. | MIT | --- testing qa automation e2e playwright jest | # Webapp Testing ## Overview Generate and execute comprehensive test suites for web applications covering unit, integration, end-t
SKILL.mdUpdated Apr 17, 2026