Review Experiment — Testing skill for Claude Code
Review an A/B test or randomized experiment — design or readout.
How to install Review Experiment
Installs to ~/.claude/skills/pitcany-statistical-agent-skills-review-experiment/SKILL.md
mkdir -p ~/.claude/skills/pitcany-statistical-agent-skills-review-experiment && curl -fsSL https://raw.githubusercontent.com/pitcany/statistical-agent-skills/HEAD/commands/review-experiment.md -o ~/.claude/skills/pitcany-statistical-agent-skills-review-experiment/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Review Experiment does
description: Review an A/B test or randomized experiment — design or readout. Covers randomization unit, SRM, power/MDE, peeking, CUPED, interference, attrition, and post-treatment adjustment.
Experiment review
Target: $ARGUMENTS
What to do
- Invoke the
experiment-designskill. - State whether this is a design review (pre-launch) or a readout review (post-launch). The procedure differs and mixing them hides defects.
- For a readout, follow the gate ordering stric
Alternatives in Testing
- Brainstorm Experiments Existing — Design experiments to test assumptions for existing products 7.8k ★
- Test TDD — Run when user calls /test-tdd 957 ★
- PR Visual Diff — Post before/after stills + GIFs on a visual PR, captured headlessly with Playwright + ffmpeg 324 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Incrementality Testing
Agent Skill for causal measurement in marketing: sample ratio mismatch, an always-valid sequential test that s
Flutter Test
Run Flutter/Dart tests, report failures, and incrementally fix test issues. Covers unit, widget, golden, and i
Ab Test Setup
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation
Discovery Experiment
Map the assumptions behind an idea and design the cheapest test that would actually change your mind, with the
12 Experiment Design
Take a scored backlog idea and write the experiment doc before any assets — hypothesis, minimum viable test, t
13 Experiment Review
Analyze a finished growth experiment — win or lose — update the pipeline, push next ideas to the backlog, syst
Related Agents
Comptroller Review
Fresh-eyes accounting-treatment & control-design review for changes that compute, display, or decide a money f
Backend Test Architect
Use this agent when you need to design, implement, or review unit tests for NextJS backend components followin
Timps Ab Testing Agent
Design A/B tests with Welch's t-test power analysis and GrowthBook configuration. Use the timps_ab_testing_age
