Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

A/B Test Readout

Turns finished experiment results into an honest readout: lift, statistical and practical significance, risks, and a ship/no-ship call.

Data & AnalyticsIntermediate★ 1,435⑂ 255AI score 8/10Last updated: Oct 10, 2026

What it does

  • Builds a control vs variant table with relative lift and p-value / confidence interval.
  • Separates statistical significance from practical significance (is the lift worth the cost?).
  • Interrogates the ways A/B tests mislead: sample/power, peeking, novelty/primacy, segment-driven wins.
  • Forces a guardrail check (revenue, retention, latency, complaints), not just the primary metric.
  • Ends with a one-line verdict (Ship / Don't ship / Inconclusive) plus monitoring and follow-up test steps.

Who it's for

  • Product managers making ship decisions from experiments
  • Growth, CRO, and marketing experimentation owners
  • Teams standardising their experiment reporting format

Examples

  1. "Control 4.2% (n=12,000), variant 4.6% (n=11,800), 14-day run — write the readout." → lift, significance reasoning, power assessment, recommendation.
  2. "Primary metric is up but refunds also rose — should we ship?" → flags the guardrail regression and argues for hold/re-run.
  3. "We stopped at day 5 because it hit significance." → warns about peeking-inflated false positives and proposes a clean re-run.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/HEAD/exports/openclaw/ab-test-readout/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the exports/openclaw/ab-test-readout folder from the GitHub repo mohitagw15856/pm-claude-skills into my ~/.claude/skills/ab-test-readout/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/mohitagw15856/pm-claude-skills.git && mkdir -p ~/.claude/skills/ab-test-readout && cp -r pm-claude-skills/exports/openclaw/ab-test-readout/* ~/.claude/skills/ab-test-readout/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open your terminal.
  2. Clone the repo: git clone https://github.com/mohitagw15856/pm-claude-skills.git
  3. Create the skill folder: mkdir -p ~/.claude/skills/ab-test-readout
  4. Copy the files: cp -r pm-claude-skills/exports/openclaw/ab-test-readout/* ~/.claude/skills/ab-test-readout/
  5. Restart Claude Code and ask something like "write an A/B test readout for these results".
  6. For a reliable verdict, supply conversions, sample size per arm, test duration, and guardrail metrics.
View source on GitHub ↗License: MIT