Growth / product analyst

A/B test reader

Immediate result: A plain-English verdict with lift, confidence interval, p-value and whether the sample is big enough.

Problem it solvesTeams call A/B tests on gut feel, ship false winners and miss real ones.

Download SKILL.md
Add this skill to
ChatGPTClaudeGeminiPerplexity

You paste

Control 10,000 visitors / 400 sign-ups · Variant 10,000 / 460 · 14 days

You get

CR: 4.0% vs 4.6% · lift +15%

z ≈ 2.09, p ≈ 0.037 · 95% CI for difference: +0.04 to +1.16 points

Verdict: likely winner — ship, and watch week-two retention.

About this skill

About A/B test reader

Teams call A/B tests on gut feel and ship false winners. This skill reads your results like a careful analyst: conversion rates and relative lift, a two-proportion z-test with p-value and a 95% confidence interval — with the arithmetic shown so anyone can check it — and a judgement on whether the sample is big enough. It gives a ship, keep running or stop verdict and names the traps that commonly fool teams, such as peeking, novelty effects and seasonality. It ends with an idea for the next test. To use it, paste the skill into your assistant and send visitors and conversions for control and each variant, and the test duration.

A/B test reader AI skill for Growth / product analyst: you paste "Control 10,000 visitors / 400 sign-ups · Variant 10,000 / 460 · 14 days" and get "CR: 4.0% vs 4.6% · lift +15%"
A/B test reader — example input and the first lines it returns. Works in ChatGPT, Claude and Gemini.
Job profile
Data & analytics · Growth / product analyst
Works in
ChatGPT, Claude, Gemini, Copilot, Claude Code
Format
Agent Skills (SKILL.md)
Price
Free, no sign-up
Install instructions

Copy, paste, send

  1. Cold email writerCopy skillCopied ✓1 Copy the skillPress Copy skill.
  2. ANY AI ASSISTANTSKILLPaste here, then press Enter2 Paste it into a new chatChatGPT, Claude, Gemini or Copilot.
  3. ANY AI ASSISTANT3 Send your inputSend visitors and conversions for control and each variant.
The skill — paste this into your AI assistant
# Skill: A/B test reader

You are running the "A/B test reader" skill for me. I work as: Growth / product analyst. What I need from you: a plain-English verdict with lift, confidence interval, p-value and whether the sample is big enough.

## When I send you visitors and conversions for control and each variant, and the test duration
1. Compute conversion rates and relative lift.
2. Run a two-proportion z-test and give the 95% confidence interval, showing the formulas.
3. Check sample size against the minimum detectable effect.
4. Give a ship / keep running / stop verdict with caveats (peeking, novelty, seasonality).

## Reply in this format
- Results table
- Statistics (with formulas)
- Verdict
- Caveats
- Next test idea

## Rules
- Show the arithmetic so it can be checked.
- Never call significance on fewer than 100 conversions per arm without a warning.
- Use only the facts I give you; mark anything you had to assume with [ASSUMPTION].
- If something essential is missing, ask me one short question, then continue.
- No preamble or filler: start with the result.

Confirm you're ready in one line, then wait for me to send visitors and conversions for control and each variant, and the test duration.

Then sendVisitors and conversions for control and each variant, and the test duration. For example: Control 10,000 visitors / 400 sign-ups · Variant 10,000 / 460 · 14 days

ChatGPT

  1. Fastest: paste the skill as your first message in a new chat, then send your input.
  2. To keep it: open a Project, choose Instructions (or Settings → Personalization → Custom instructions for every chat) and paste it there.
  3. To share it with a team: create a custom GPT and paste the skill into its Instructions.
  4. In the Codex app: copy the skill's folder into ~/.codex/skills/ (or Customize → Skills → Add → Create skill).

Claude

  1. Fastest: paste the skill as your first message in a new chat, then send your input.
  2. To keep it: create a Project, open Project instructions and paste the skill.
  3. As a Claude Skill: download the skill's ZIP, then in Claude open Settings → Skills → Add → Upload skill and choose the file.

Gemini

  1. Fastest: paste the skill as your first message in a new chat, then send your input.
  2. To keep it: open Gems → New Gem, paste the skill into Instructions and save.

Microsoft Copilot

  1. Fastest: paste the skill as your first message, then send your input.
  2. In Microsoft 365 Copilot, save it as a prompt or paste it into an agent's instructions to reuse it.

Any other assistant

  1. Paste the skill as the system prompt or first message in any chat assistant (Perplexity, Meta AI, DeepSeek, Mistral, local models).
  2. Coding agents that read the Agent Skills format (SKILL.md) can load the downloaded file from their skills folder.

Install it permanently

Upload it to Claude, add it to ChatGPT's Codex app, clone it into Claude Code, or download the SKILL.md for any agent. Full guide with screenshots →

Download the ZIP and upload it in Claude. Claude then uses the skill on its own whenever a request matches.

Download ZIP

Quick setup

  1. In Claude, open Settings → Skills (under Customize).
  2. Click Add → Upload skill.
  3. Choose the ZIP — don't unzip it — and make sure the skill is switched on.
Claude Settings with Skills selected under Customize, and the Add menu open showing Upload skill, Create a skill, Create with Claude and Record your screen

Repositoryscienceofapps.com/skills/ai-skills.git · all 200 skills, one folder each, plain git over HTTPS

What it does

The steps it follows

  1. Compute conversion rates and relative lift.
  2. Run a two-proportion z-test and give the 95% confidence interval, showing the formulas.
  3. Check sample size against the minimum detectable effect.
  4. Give a ship / keep running / stop verdict with caveats (peeking, novelty, seasonality).
What you get back

The reply format

  • Results table
  • Statistics (with formulas)
  • Verdict
  • Caveats
  • Next test idea

Rules it never breaks

  • Show the arithmetic so it can be checked.
  • Never call significance on fewer than 100 conversions per arm without a warning.
  • Uses only the facts you give it and marks assumptions.
FAQs

Questions about A/B test reader

What does the A/B test reader skill do?

Teams call A/B tests on gut feel, ship false winners and miss real ones. The skill fixes that: a plain-English verdict with lift, confidence interval, p-value and whether the sample is big enough.

How do I install A/B test reader in ChatGPT, Claude or Gemini?

Copy the skill and paste it as the first message of a new chat, then send your input. To keep it, paste it into a ChatGPT Project or custom GPT, a Claude Project or a Gemini Gem, or upload the SKILL.md file as a Claude Skill.

What do I send A/B test reader after installing it?

Send visitors and conversions for control and each variant, and the test duration. If something essential is missing, the skill asks you one short question and then continues.

Is the A/B test reader skill free?

Yes. It's free to copy, use and adapt, with no sign-up, and works in the free versions of ChatGPT, Claude, Gemini and Copilot.

More for data & analytics
Data analyst

Data cleaning plan

ProblemA messy export has duplicates, mixed formats and blanks, and cleaning it by hand is error-prone.

You paste

pandas · columns: name, phone, city, signup_date (formats: 03/10/26, 2026-10-03, '3 Oct')

You get

signup_date: 3 formats → pd.to_datetime(df.signup_date, dayfirst=True, format='mixed')

city: 'Bombay'/'Mumbai '/'mumbai' → strip, title-case, map Bombay → Mumbai

Check: rows before = rows after + duplicates removed (logged).

Immediate resultA step-by-step cleaning plan with the code (pandas, SQL or spreadsheet steps) to do it.

How to use it
Analytics lead / PM

Dashboard spec writer

ProblemDashboards get built with every metric and answer no question.

You paste

Weekly dashboard for the head of a food-delivery city team

You get

Q1: Are we delivering on time? → On-time rate = orders delivered ≤ promised ETA ÷ delivered orders

Chart: line, 8 weeks, with target line at 92%

Filter: zone, hour of day.

Immediate resultA dashboard spec: the questions it answers, metrics with definitions, charts, filters and layout.

How to use it
Analytics engineer / data analyst

Metric definition doc

ProblemTwo teams report different numbers for 'active users' because nobody wrote the definition down.

You paste

'Activation rate' for a B2B SaaS — people mean different things

You get

Activation rate = new workspaces that invite ≥ 1 teammate and create ≥ 1 project within 7 days ÷ new workspaces

Excludes: internal and test workspaces (domain list).

Edge: workspaces created on day 6 of the window are counted next week.

Immediate resultA precise metric definition: formula, inclusions, exclusions, grain, owner and SQL.

How to use it

All 14 data & analytics skillsAll 200 skillsRead it in the articleProve it: AI for Data Analysts Certification (free test)

Free PDF · 74 pages · 2 editions

The Laws of UX, in one field guide

60 research-backed principles in 6 categories — what each one means, why it works on the human brain and how to use it on your own screens. Written by Sushant Singh, founder of Science of Apps, who has scaled consumer apps to lacs of users and spent 10+ years leading product across startups and digital businesses in the US, EU & India.

Pick your edition
Free. No card, no paywall — just your email.
Free PDF · 74 pages

Get Laws of UX by email

Choose your edition

You’ll also get occasional UX psychology tips. Unsubscribe anytime. Privacy policy

Free PDF · 90 pages · 2 editions

100+ Subscription Paywalls, decoded

110 real paywalls from top apps, taken apart, rated out of 5 and decoded with the Laws of UX — plus the frameworks, copy and checklists to ship your own. By Sushant Singh, founder of Science of Apps.

  • 110 paywalls rated
  • 34 Laws of UX
  • 12 frameworks

Which paywall scored 4.8 out of 5, and which scored 2.6? It’s all inside.

Pick your edition
Free. No card, no paywall — just your email.
Free PDF · 90 pages

Get 100+ Paywalls, Decoded by email

Choose your edition

You’ll also get occasional UX psychology tips. Unsubscribe anytime. Privacy policy