Skills
.Work. You
Rest

experiment-metrics

Official

Score trustworthy experiment metrics with STEDII

Product & Management#data-analytics#guardrails#ab-testing#metrics-framework#stedii#experiment-metrics#statistical-power
Authorcoalesce-labs
Version1.0.0
Installs0

System Documentation

What problem does it solve?

STEDII framework helps teams select trustworthy experiment metrics, ensuring metric validity and reliability to guide data-driven decisions.

Core Features & Use Cases

  • Defines a primary metric and 3-5 guardrail metrics for experiments.
  • Provides a six-dimension STEDII scoring rubric (Sensitive, Timely, Efficient, Debuggable, Interpretable, Isolated) to evaluate candidate metrics.
  • Includes pre-experiment checks (A/A sanity checks, variance assessment, sample size planning) and guidance for segmentation planning.
  • Offers a structured decision framework and practical examples to apply metrics decisions in real projects.

Quick Start

Define a primary metric and 3-5 guardrail metrics for your upcoming experiment using the STEDII framework and validate readiness with a pre-experiment checklist.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: experiment-metrics
Download link: https://github.com/coalesce-labs/catalyst/archive/main.zip#experiment-metrics

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.