analytics-analyst

Design analytics tracking implementations and A/B test plans for marketing measurement.

12|2|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/jikig-ai/soleur --skill analytics-analyst
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: analytics-analyst
Source: https://github.com/jikig-ai/soleur/tree/main/.openhands/skills/analytics-analyst
Command: npx skills add https://github.com/jikig-ai/soleur --skill analytics-analyst

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes ambiguity and measurement gaps in marketing analytics by producing clear event taxonomies, implementation-ready specs, statistically sound A/B test plans, and channel-specific attribution reports so teams can trust their metrics and decisions.

Core Features & Use Cases

  • Event taxonomy & tracking specs: delivers event names, properties, triggers, and implementation tables before any code is written.
  • A/B test design & analysis: creates hypotheses, primary metrics, sample size calculations (power analysis), MDE defaults, and duration estimates.
  • Attribution modeling & audits: compares or produces single-model attribution reports (last-touch, first-touch, linear, time-decay, data-driven) and flags GA4 retention and implementation issues.
  • Use Case: instrument a marketing landing page, plan an A/B experiment with required sample size and duration, and generate an attribution report for channel performance.

Quick Start

Use the analytics-analyst skill to produce an event taxonomy, sample size calculation with default MDE, and an attribution model report for a new marketing campaign.

Frequently Asked Questions about analytics-analyst

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design an A/B test with the right sample size and duration?

A/B test design requires defining hypotheses, primary metrics, and minimum detectable effect (MDE) defaults to calculate sample size and estimate test duration, ensuring statistically sound experiment plans for accurate marketing measurement.

What is an event taxonomy and how does it improve GA4 tracking?

An event taxonomy defines event names, properties, and triggers before implementation. Building a structured event taxonomy improves GA4 tracking by removing measurement gaps and producing implementation-ready property lists for accurate data collection.

How do I set up attribution modeling across acquisition channels?

Attribution modeling assigns credit across acquisition channels using single-model approaches like last-touch, first-touch, linear, time-decay, or data-driven. Generating model-specific attribution reports flags GA4 retention issues and compares channel performance.

Can I use power analysis to calculate MDE defaults for marketing experiments?

Power analysis calculates required sample sizes by stating MDE defaults for marketing experiments. This statistical method determines the minimum effect size an A/B test can reliably detect, ensuring experiments are properly powered before launch.

What is the best way to audit marketing analytics tracking implementations?

Auditing marketing analytics tracking implementations involves reviewing event taxonomies and property lists against current specs. A rigorous tracking audit flags GA4 retention and implementation issues, ensuring measurement gaps are identified and resolved.