Growth PM

Experiment designer

Immediate result: An experiment plan with hypothesis, variants, metric, sample size, duration and decision rule.

Problem it solvesExperiments launch without a hypothesis or success criteria, so results get argued about.

Add this skill to

You paste

Test a one-page checkout vs three steps · baseline conversion 3% · 8,000 checkouts/week

You get

Hypothesis: because 40% drop at the address step, one page will raise conversion for mobile users.

To detect +15% relative (3.0 → 3.45%) at 80% power: ~24,000 per arm ≈ 6 weeks.

Decision rule: ship if p < 0.05 and refund rate is unchanged.

About this skill

About Experiment designer

Experiments launched without a hypothesis or success criteria end in arguments about what the result means. This skill writes the plan before launch: a hypothesis grounded in evidence, the variants, primary, secondary and guardrail metrics, the sample size and duration needed for your minimum detectable effect — with the formula and inputs shown — and a decision rule agreed in advance. It also lists risks such as novelty effects. Agreeing the rule before seeing data is what makes an experiment trustworthy. To use it, paste the skill into your assistant and send the change you want to test, the metric it should move, current baseline and traffic; the reply opens with “Hypothesis”.

Experiment designer AI skill for Growth PM: you paste "Test a one-page checkout vs three steps · baseline conversion 3% · 8,000 checkouts/week" and get "Hypothesis: because 40% drop at the address step, one page will raise conversion for mobile users."
Experiment designer — example input and the first lines it returns. Works in ChatGPT, Claude and Gemini.
Job profile
Product management · Growth PM
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 the change you want to test.
The skill — paste this into your AI assistant
# Skill: Experiment designer

You are running the "Experiment designer" skill for me. I work as: Growth PM. What I need from you: an experiment plan with hypothesis, variants, metric, sample size, duration and decision rule.

## When I send you the change I want to test, the metric it should move, current baseline and traffic
1. Write the hypothesis: because [evidence], we believe [change] will [effect] for [users].
2. Define primary, secondary and guardrail metrics.
3. Estimate sample size and duration for the minimum detectable effect, showing the formula.
4. Set the decision rule before launch.

## Reply in this format
- Hypothesis
- Variants
- Metrics
- Sample size and duration
- Decision rule
- Risks

## Rules
- Show the sample size formula and inputs.
- 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 the change I want to test, the metric it should move, current baseline and traffic.

Then sendThe change you want to test, the metric it should move, current baseline and traffic. For example: Test a one-page checkout vs three steps · baseline conversion 3% · 8,000 checkouts/week

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. Write the hypothesis: because [evidence], we believe [change] will [effect] for [users].
  2. Define primary, secondary and guardrail metrics.
  3. Estimate sample size and duration for the minimum detectable effect, showing the formula.
  4. Set the decision rule before launch.
What you get back

The reply format

  • Hypothesis
  • Variants
  • Metrics
  • Sample size and duration
  • Decision rule
  • Risks

Rules it never breaks

  • Show the sample size formula and inputs.
  • Uses only the facts you give it and marks assumptions.
FAQs

Questions about Experiment designer

What does the Experiment designer skill do?

Experiments launch without a hypothesis or success criteria, so results get argued about. The skill fixes that: an experiment plan with hypothesis, variants, metric, sample size, duration and decision rule.

How do I install Experiment designer 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 Experiment designer after installing it?

Send the change you want to test, the metric it should move, current baseline and traffic. If something essential is missing, the skill asks you one short question and then continues.

Is the Experiment designer 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 product management
PM / product marketer

Release notes writer

ProblemRelease notes are a list of ticket titles that users don't understand or care about.

You paste

PAY-201 add UPI autopay · BUG-88 fix crash on Android 14 · UX-12 faster search

You get

New: Set up UPI Autopay once and never miss a bill.

Improved: Search results now appear as you type.

Fixed: the app no longer closes unexpectedly on some Android 14 phones.

Immediate resultUser-facing release notes that lead with benefits, plus an internal changelog version.

Product manager

Stakeholder update

ProblemWeekly updates are long, unstructured and hide the one decision leadership needs to make.

You paste

Notes: payment integration delayed by bank sandbox, design done, beta users 40/100

You get

Status: Amber — bank sandbox access is 1 week late.

Decision needed: launch beta with card payments only? (yes/no by Thu)

Progress: design complete; 40 of 100 beta users recruited.

Immediate resultA five-line update: status, progress, risks, decisions needed and next steps.

PM / support lead

Feedback triage

ProblemFeature requests arrive from sales, support and app reviews with no way to compare them.

You paste

60 feedback items from Intercom, sales calls and Play Store reviews

You get

Problem: can't share reports with clients — 14 mentions (9 agency accounts)

Request 'add PDF export' → problem 'need a client-ready report'.

Investigate: client sharing, bulk edit, Hindi support.

Immediate resultFeedback grouped into problems (not solutions), counted, with segment and revenue impact.

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