Is this skill grounded in industry standards?

Yes, the skill is grounded in standards from SWEBOK and AIPMM, utilizing proven frameworks like Lean Analytics and Marty Cagan's product principles.

How does this skill help avoid vanity metrics?

It implements a rigorous metrics hierarchy that prioritizes quality and retention over simple volume, ensuring focus on indicators that reflect true business value.

Can I use this for A/B testing design?

Yes, the skill provides standardized templates for defining success criteria, establishing baselines, and setting targets required for valid A/B tests.

What is the difference between leading and lagging indicators in this skill?

Leading indicators provide early signals that predict future performance, while lagging indicators measure the final business results, allowing for proactive adjustments.

Experiment Design & Product Analytics

Name: Experiment Design & Product Analytics
Author: sethdford

bysethdford

•

분석 및 모니터링

Designs data-informed experimentation frameworks and metric hierarchies to measure product performance and user behavior effectively.

The Experiment Design skill empowers Product Managers and developers to move beyond vanity metrics by establishing robust measurement frameworks. It facilitates the creation of comprehensive metrics hierarchies—ranging from North Star strategic goals to granular diagnostic indicators—while ensuring a clear distinction between causation and correlation. By guiding users through cohort analysis and experimentation velocity, this skill helps teams identify leading indicators, set realistic performance targets, and systematically investigate metric fluctuations to drive evidence-based product decisions grounded in SWEBOK and AIPMM standards.

주요 기능

01Metric hierarchy mapping from strategic to diagnostic levels

025 GitHub stars

03Cohort analysis framework for long-term behavior tracking

04LLM error mitigation for vanity metric anti-patterns

05Experimentation plan generation with success criteria and baselines

06Leading and lagging indicator identification and tracking

사용 사례

01Investigating metric fluctuations to distinguish between correlation and causation

02Designing a structured experimentation plan to validate high-impact product hypotheses

03Defining a North Star metric and supporting KPIs for a new product feature launch

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sethdford/claude-skills experiment-design

For use in Claude.ai and ChatGPT

주요 기능

01Metric hierarchy mapping from strategic to diagnostic levels

025 GitHub stars

03Cohort analysis framework for long-term behavior tracking

04LLM error mitigation for vanity metric anti-patterns

05Experimentation plan generation with success criteria and baselines

06Leading and lagging indicator identification and tracking

사용 사례

01Investigating metric fluctuations to distinguish between correlation and causation

02Designing a structured experimentation plan to validate high-impact product hypotheses

03Defining a North Star metric and supporting KPIs for a new product feature launch