Verified:GitHub

Experiment Tracker

Design and analyze statistically valid experiments for product decisions.

Updated Apr 16, 2026

Search Tags:#product management #experiment design #hypothesis testing #data-driven #a/b testing #statistical analysis #experiment tracking

Ready to run

npx skills add https://github.com/jc180105/.opencode --skill experiment-tracker-jc180105

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Experiment Tracker
Source: https://github.com/jc180105/.opencode/tree/main/.opencode/skills/project-management-experiment-tracker
Command: npx skills add https://github.com/jc180105/.opencode --skill experiment-tracker-jc180105

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Expert project managers often struggle to validate product decisions without reliable experimentation, leading to wasted resources and uncertain risk. This Skill provides structured processes to design, execute, and learn from experiments with rigorous data analysis.

Core Features & Use Cases

Experiment Design & Planning: Create clear hypotheses, determine sample sizes, and define success criteria for reliable results.
Portfolio & Execution Management: Manage multiple experiments with lifecycle tracking, instrumentation quality, and rollback procedures.
Decision Support & Learnings: Translate results into actionable business insights and shared organizational learning.

Quick Start

Draft a complete experiment plan for a feature test, including hypothesis, metrics, sample size, and rollout plan.

Frequently Asked Questions about Experiment Tracker

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

FAQPage Schema

How do I calculate sample size for an A/B test to ensure valid product decisions?▼

To calculate sample size for an A/B test, you formulate a clear hypothesis and define success criteria upfront. This ensures your experiment tracks reliable data and achieves statistically valid results for your product decisions.

What is the best way to manage multiple A/B tests across web and mobile features?▼

The best way to manage multiple A/B tests is using portfolio and execution management to track experiment lifecycles. This includes monitoring instrumentation quality and maintaining rollback procedures across web and mobile features.

How do I formulate a hypothesis for multi-variant experiments and data-driven investigations?▼

To formulate a hypothesis for multi-variant experiments, you design structured tests with clear success criteria and randomization rules. This approach supports rigorous data-driven investigations and statistical analysis across product features.

Does this experiment design process support safety monitoring and rollback procedures?▼

Yes, experiment design supports safety monitoring and rollback procedures. It incorporates lifecycle tracking and instrumentation quality checks to manage risk, allowing you to safely halt or rollback web and mobile feature tests.

When do I need statistical analysis for hypothesis testing in product management?▼

You need statistical analysis for hypothesis testing in product management when validating decisions through A/B tests or multi-variant experiments. It translates raw experiment data into actionable business insights and shared organizational learning.

How do I document experiment results to translate statistical analysis into business insights?▼

To document experiment results, you use rigorous results documentation to translate statistical analysis into actionable business insights. This process captures shared organizational learnings from your hypothesis-driven investigations and feature tests.