How does it handle anomalies in data?

The skill specifically looks for sudden spikes or drops and identifies correlations between different metrics to help you attribute the cause to specific events, segments, or external factors.

Does it help with setting product goals?

Yes, it includes frameworks for OKRs and provides guidance on setting realistic metric targets based on your current baselines and industry benchmarks.

Can this skill connect to my existing analytics tools?

Yes, if you have product analytics connectors configured in your environment, the skill can pull data automatically. Otherwise, it will prompt you to provide data manually.

What types of metrics does it support?

It covers the entire user lifecycle, including acquisition (signups), activation, engagement (DAU/MAU), retention, monetization (ARR/MRR), and satisfaction (NPS).

Product Metrics Review

Name: Product Metrics Review
Author: anthropics

byanthropics

•

11,566

•

Analytics & Monitoring

Analyzes product performance data to identify trends, compare against targets, and generate actionable strategic insights.

The Metrics Review skill empowers product managers and knowledge workers to transform raw data into a structured performance analysis. It automates the process of evaluating the Product Metrics Hierarchy—from North Star metrics to L1 health indicators like acquisition, retention, and monetization. By identifying anomalies, correlating trends, and benchmarking against OKRs, the skill provides a comprehensive scorecard and recommended actions to drive product growth and data-informed decision-making.

Key Features

01Automated metric scorecard generation with status tracking

02Support for Product Metrics Hierarchy (North Star, L1, and L2 metrics)

0311,566 GitHub stars

04Integration with product analytics connectors for automated data retrieval

05Comprehensive trend analysis including acceleration and anomaly detection

06Actionable recommendation engine for experiments and investigations

Use Cases

01Conducting weekly, monthly, or quarterly product performance reviews

02Investigating sudden spikes or drops in key user engagement metrics

03Comparing actual product performance against established OKR targets

Key Features

01Automated metric scorecard generation with status tracking

02Support for Product Metrics Hierarchy (North Star, L1, and L2 metrics)

0311,566 GitHub stars

04Integration with product analytics connectors for automated data retrieval

05Comprehensive trend analysis including acceleration and anomaly detection

06Actionable recommendation engine for experiments and investigations

Use Cases

01Conducting weekly, monthly, or quarterly product performance reviews

02Investigating sudden spikes or drops in key user engagement metrics

03Comparing actual product performance against established OKR targets