experiment-tracker

Manage product experiment lifecycles with hypothesis validation and statistical analysis.

2|Updated Jun 30, 2026
One-click install
npx skills add https://github.com/Canhada-Labs/ceo-orchestration --skill experiment-tracker-canhada-labs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: experiment-tracker
Source: https://github.com/Canhada-Labs/ceo-orchestration/tree/main/.claude/skills/domains/project-management/skills/experiment-tracker
Command: npx skills add https://github.com/Canhada-Labs/ceo-orchestration --skill experiment-tracker-canhada-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

The Experiment Tracker Skill helps teams manage the entire lifecycle of product experiments, ensuring they are conducted ethically, effectively, and with thorough analysis.

Core Features & Use Cases

  • Hypothesis Management: Create and review hypotheses for experiments with required criteria like falsifiable statements, primary metrics, and sample size calculations.
  • Experiment Design QA: Ensures all experiments go through a mandatory design-QA gate with checks for power analysis and mutual-exclusion configuration.
  • Results Synthesis: Synthesizes results with statistical analysis, effect size, and confidence intervals, flagging post-hoc segmentation or criteria changes as invalid.

Quick Start

Run 'start_experiment experiment-id hypothesis primary-metric guardrail-metric sample-size owner min-runtime status'

Frequently Asked Questions about experiment-tracker

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

FAQPage Schema
How do I manage the entire product experiment lifecycle from hypothesis to results?

Product experiment lifecycle management requires structured hypothesis development, mandatory design-QA gates for power analysis, and rigorous results synthesis to ensure statistical validity and prevent post-hoc rationalization.

What is the best way to prevent post-hoc segmentation during experiment analysis?

Preventing post-hoc segmentation requires an experimentation framework with built-in guardrails that automatically flag criteria changes and invalid segmentations during results synthesis to maintain statistical integrity.

How do I set up a product experiment with proper falsifiable hypotheses and sample size calculations?

Setting up valid product experiments requires defining falsifiable hypothesis statements, identifying primary and guardrail metrics, calculating sample sizes, and configuring mutual-exclusion before execution begins.

Does rigorous experiment management work for teams needing ethical testing guardrails?

Rigorous experiment management is designed specifically for teams requiring ethical testing practices, offering robust validation criteria and mandatory design-QA gates to prevent experiment misuse.

Why do I need power analysis and mutual-exclusion configuration before running product tests?

Power analysis and mutual-exclusion configuration are mandatory design-QA checks needed to ensure your product tests have adequate sample sizes and prevent overlapping experiments from contaminating results.

Can I synthesize experiment results with confidence intervals and effect size measurements?

Synthesizing experiment results involves statistical analysis incorporating effect size and confidence intervals to provide a comprehensive view of product testing outcomes and validate primary metrics.