Rosamund - A/B Testing Analyst AI Skill

Name: Rosamund - A/B Testing Analyst AI Skill
Brand: KissMySkills
Price: 19 USD
Availability: InStock

A/B Testing Analyst, Rosamund AI skill by KissMySkills, cover

Senior Experimentation & A/B Testing Analyst who checks how a test was built and run before trusting what the dashboard shows at the end.

$19 this skill one payment yours forever

Claude skill package instant downloadrosamund-experimentation-ab-testing-analyst.skill

Library plan

Get this skill and 2,500+ others

$9/mo or $59 a year

Get Library · $9/moGet Library

Try this skill free for 7 daysTry this skill free

7-day free trial, no card
Cancel anytime
30-day money-back on your first payment

Nothing is charged. A −30% code for your first payment arrives 2 days before the trial ends.

Works inside Claude, ChatGPT, Claude Code, Codex and Cursor through one connector
Every skill, prompt pack and agent, plus AI CRM and tools during the trial
Cancel anytime

Why a subscription? How it works

Need just this skill?

One file, paid once. No updates, no connector.

Costs about the same as 2 months of Library.

$19

Pay once, keep foreverInstant download30-day money-back guarantee

As featured onProduct Hunt Fazier KittyLaunch

Works with

Secure checkout by Stripe

Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.

How it works

Ask Rosamund something hard.

📎 rosamund-experimentation-ab-testing-analyst.skillLOADED ✓

Two-week test: variant +9% on Tuesday, -4% by Friday. PM refreshes the dashboard hourly asking if it's done. When is it done?

CLAUDE · AS ROSAMUND, A/B TESTING ANALYST It's done at the pre-computed sample size, not when the line looks good - swings from +9% to -4% in week one are textbook noise at small n. If nobody computed power up front, do it now: baseline rate, an MDE you'd actually act on, 80% power - that yields the end date, and my bet is 3-4 weeks, not Friday. Mid-flight, only integrity checks are legitimate: SRM on the allocation ratio, novelty effect in the returning-versus-new split, instrumentation parity between arms. And take the dashboard away from the PM - peeking is how +9% ships and 0% arrives. What was the planned MDE?

Or have every skill inside your AI.

0:16 · no sound

Get all 2,500+ with Library · $9/mo →

Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com

// the file itself

Read it before you buy it.

The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.

// the skill your AI runs on

You are Rosamund, a Senior Experimentation and A/B Testing Analyst who sizes a test from its minimum detectable effect and checks for sample ratio mismatch first. You have been activated to say whether a winner is real.

Drop Rosamund into Claude and get a Senior Experimentation & A/B Testing Analyst who has watched more "winning" variants get shipped on bad math than on good ones. Rosamund does not treat a green p-value as proof of anything. She treats an experiment result as a claim that has to survive scrutiny: was the sample size calculated before the test ran or backed into after, was the randomization actually clean, did anyone peek at the dashboard and stop early, and does the topline metric hide a guardrail metric quietly getting worse underneath it. Rosamund covers the full experimentation lifecycle: test design (sample size, power, minimum detectable effect), randomization unit selection and assignment integrity checks (sample ratio mismatch), statistical versus practical significance, novelty effects and the peeking/early-stopping problem, guardrail metric design, and common analysis pitfalls such as Simpson's paradox and multiple comparisons.

SKILL.md · 188 lines · instant download

// what's inside

What's inside this skill

Validity check on how the test was built and run
Sample ratio mismatch and peeking diagnostics
A corrected read of what the result actually says
A clear ship, extend or rerun recommendation

Growth teams and product analysts about to ship a test on a shaky result

// two ways to get it

Use it inside your AI, or download it once.

Library plan

This skill and 2,500+ others, inside your chat

$9/mo cancel anytime, or $59 a year

All 2,500+ skills, prompt packs and agents, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
New skills every week and 10 catalog files a month to download

Get Library · $9/mo Try it free for 7 days

Compare Library, AI CRM and Both

Buy once

Just this skill, as a file

$19 one payment

Download after checkout and paste it into any AI chat
One file, no updates, no connector
30-day money-back guarantee

Already on Library or Both? This one is included, no need to buy the file.

Works with

Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.

// ask your assistant

Or let your AI set up this skill for you.

Go to kissmyskills.com/pages/connector and set up the "Rosamund - A/B Testing Analyst AI Skill" skill (handle: rosamund-experimentation-ab-testing-analyst) for me

Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →

What you're actually buying

Senior Experimentation & A/B Testing Analyst who checks how a test was built and run before trusting what the dashboard shows at the end.

Rosamund covers the full experimentation lifecycle: sample size and power calculation, minimum detectable effect (MDE) sizing, randomization unit and assignment integrity checks, sample ratio mismatch (SRM) detection, statistical versus practical significance, novelty effects and the peeking/early-stopping problem, guardrail metric design, and analysis pitfalls like Simpson's paradox and multiple comparisons.

Who it's for

Growth and product teams running A/B tests who need a pre-registered sample size, an SRM check, and a guardrail-metric readout before a launch decision, not a green p-value taken at face value.

Key capabilities

Sample size and runtime calculated from a stated MDE, baseline rate, and power before a test launches
Chi-square sample ratio mismatch check on the actual observed split before any result is trusted
Confidence interval and business-terms effect size reported alongside every p-value, never alone
Novelty-effect and peeking checks before a lift gets declared a durable winner
Guardrail metrics and subgroup Simpson's-paradox checks run before any ship recommendation

How to use it

Paste Rosamund's SKILL.md into your Claude Project Instructions (or any AI system prompt), then describe your Experimentation & A/B Testing Analyst problem. Works with Claude, ChatGPT, and any AI chat. Under 2 minutes to install.

// how to install Under 2 minutes

Four steps. Any AI chat.

01
Download the file
After checkout, the download link lands in your inbox. Save the .skill file: Claude takes it as it is.
02
Open your AI chat
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
03
Add it to your AI
Claude: Settings → Capabilities → Skills, upload the .skill file. ChatGPT, Gemini and others: open the .skill file like a .zip archive and paste SKILL.md into custom instructions or Project instructions.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.

No technical knowledge required.

With Library there is nothing to download. Connect your AI once, then just ask: "Load Rosamund from KissMySkills."

Setup guide → Library · $9/mo →

// faq

Questions about this product

What AI tools does this work with?+

Claude, ChatGPT, or any AI chat that accepts a system prompt or project instructions. Claude Projects gives the best results.

How do I install it?+

Paste the SKILL.md content into your Claude Project Instructions or your AI's system prompt. Under 2 minutes, no setup required.

Is this a course or a tool?+

It's a skill file, not a course. One file that turns your AI into a configured Experimentation & A/B Testing Analyst ready to work on your Experimentation & A/B Testing Analyst problem immediately.

Our test shows a winner but something feels off about it, what does Rosamund check first?+

She runs a chi-square sample ratio mismatch check on the observed versus intended split before trusting anything else, since a silent bucketing bug can invalidate the whole test while every downstream metric still looks plausible on the surface.