A/B Test Plan Builder
Produces a statistically rigorous A/B or multivariate test spec — hypothesis, sample size, guardrails, and stopping rules.
Marketing & SEOIntermediate★ 728⑂ 124AI score 8/10Last updated: Aug 9, 2026
What it does
Give it the element you want to test (headline, CTA button, pricing layout, checkout flow), your baseline conversion rate, and daily traffic — and it returns a complete, pre-registered experiment specification.
- If/Then/Because hypothesis statement grounded in data or UX principle
- Sample size calculation at 95% significance and 80% power by default
- Absolute vs. relative MDE clarification — the most common sample-size mistake; at a 5% baseline the two readings differ by roughly 200×
- Test duration estimate (7-day minimum business cycle, validity warning past 8 weeks)
- Primary, secondary, and guardrail metric definitions
- Monitoring plan with SRM (sample ratio mismatch) detection and technical QA checkpoints (not statistical peeking)
- Stopping rules and Go/No-Go criteria, plus a protocol for inconclusive results
- Traffic feasibility check with low-traffic alternatives
Who it's for
- CRO and growth practitioners running a real experimentation program
- Marketers who have been eyeballing "is this significant?"
- Low-traffic startups that need to know whether a test is even feasible
- Product teams that want experiment learnings documented as an asset
Examples
- Landing page headline test: "3.2% conversion, 1,800 visitors/day, want to catch a +0.5pp lift" → per-variant sample size, estimated run days, and a flag if it exceeds 8 weeks.
- Checkout flow shortening: designs a 2-step variant against the 3-step control, sets completion rate as primary, and monitors refund rate and AOV as guardrails.
- Multivariate design: builds a 2 CTA copies × 2 button colors matrix, and if traffic is thin, recommends cutting variants, raising the MDE, or switching to qualitative research.
· · · 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/indranilbanerjee/digital-marketing-pro/HEAD/skills/ab-test-plan/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)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the 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 skills/ab-test-plan folder from the GitHub repo indranilbanerjee/digital-marketing-pro into my ~/.claude/skills/ab-test-plan/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/indranilbanerjee/digital-marketing-pro.git && mkdir -p ~/.claude/skills && cp -r digital-marketing-pro/skills/ab-test-plan ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/indranilbanerjee/digital-marketing-pro.git - Create the skills directory:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r digital-marketing-pro/skills/ab-test-plan ~/.claude/skills/ - This skill calls
scripts/sample-size-calculator.py,significance-tester.py, andcampaign-tracker.py. Copy the repo'sscripts/folder too, or install the whole repo as a Claude Code plugin so${CLAUDE_PLUGIN_ROOT}resolves correctly. - Python 3 is required; if imports fail, run
pip install scipy. - Restart Claude Code and try: "Plan an A/B test for my landing page CTA button."
- For brand voice, run
/digital-marketing-pro:brand-setupfirst to create a brand profile. Without one, the skill falls back to defaults.
View source on GitHub ↗License: MIT