data-analytics

Analyze funnels and generate SQL for BigQuery or Redshift.

8|1|Updated Dec 28, 2025
One-click install
npx skills add https://github.com/officebeats/beats-pm-antigravity-brain --skill data-analytics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analytics
Source: https://github.com/officebeats/beats-pm-antigravity-brain/tree/main/.agent/skills/data-analytics
Command: npx skills add https://github.com/officebeats/beats-pm-antigravity-brain --skill data-analytics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manual funnel analysis and metric planning are time-consuming and error-prone. This Skill provides a structured approach to define key metrics, generate SQL for data warehouses, and design experiments to drive data-informed decisions.

Core Features & Use Cases

  • Metric Definition: Define P0/P1 metrics for product features and funnels.
  • SQL Generation: Draft SQL queries for BigQuery/Redshift to calculate metrics and identify drop-offs.
  • Experiment Design: Calculate sample sizes and define success criteria for feature tests and experiments.

Quick Start

Describe your funnel and let the AI generate SQL, define metrics, and plan experiments.

Frequently Asked Questions about data-analytics

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

FAQPage Schema
How do I define P0 and P1 metrics for funnel analysis?

To define P0 and P1 metrics for funnel analysis, you describe your product funnel, and the system structures these key performance indicators to quantify product performance and track critical drop-off points.

Can I generate BigQuery and Redshift SQL queries for calculating funnel metrics?

Yes, you can generate BigQuery and Redshift SQL queries for calculating funnel metrics. By describing your funnel, the system drafts the exact SQL needed to calculate metrics and identify user drop-offs.

What is the best way to calculate sample sizes for product experimentation?

The best way to calculate sample sizes for product experimentation is using a structured experiment design approach. This system calculates required sample sizes and defines success criteria for your feature tests.

Does this approach work for marketing analytics and SQL-backed data warehouses?

Yes, this approach works for marketing analytics and SQL-backed data warehouses. It provides a structured method to define metrics, generate warehouse SQL, and design experiments for data-informed decisions.

How do I identify drop-offs in my product funnel using SQL?

To identify drop-offs in your product funnel using SQL, the system generates targeted BigQuery or Redshift queries that calculate your defined metrics and pinpoint exactly where users exit the funnel.