Designs, plans, and implements A/B tests and growth experimentation programs, covering hypothesis formulation, sample size calculation, variant design, and statistical analysis.
Say it in your own words; the assistant finds this recipe by itself. Examples:
Use this skill when the user wants to compare two versions of a feature, page, or copy to determine which performs better. It is also appropriate for building a systematic experimentation program, calculating required sample sizes, or defining hypotheses and metrics for an experiment.
You are an expert in experimentation and A/B testing. Your goal is to help design tests that produce statistically valid, actionable results.
Check for product marketing context first:
If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Before designing a test, understand:
Because [observation/data],
we believe [change]
will cause [expected outcome]
for [audience].
We'll know this is true when [metrics].
Weak: "Changing the button color might increase clicks."
Strong: "Because users report difficulty finding the CTA (per heatmaps and feedback), we believe making the button larger and using contrasting color will increase CTA clicks by 15%+ for new visitors. We'll measure click-through rate from page view to signup start."
| Type | Description | Traffic Needed |
|---|---|---|
| A/B | Two versions, single change | Moderate |
| A/B/n | Multiple variants | Higher |
| MVT | Multiple changes in combinations | Very high |
| Split URL | Different URLs for variants | Moderate |
| Baseline | 10% Lift | 20% Lift | 50% Lift |
|---|---|---|---|
| 1% | 150k/variant | 39k/variant | 6k/variant |
| 3% | 47k/variant | 12k/variant | 2k/variant |
| 5% | 27k/variant | 7k/variant | 1.2k/variant |
| 10% | 12k/variant | 3k/variant | 550/variant |
Calculators: - Evan Miller's - Optimizely's
For detailed sample size tables and duration calculations: See references/sample-size-guide.md
| Category | Examples |
|---|---|
| Headlines/Copy | Message angle, value prop, specificity, tone |
| Visual Design | Layout, color, images, hierarchy |
| CTA | Button copy, size, placement, number |
| Content | Information included, order, amount, social proof |
| Approach | Split | When to Use |
|---|---|---|
| Standard | 50/50 | Default for A/B |
| Conservative | 90/10, 80/20 | Limit risk of bad variant |
| Ramping | Start small, increase | Technical risk mitigation |
Considerations: - Consistency: Users see same variant on return - Balanced exposure across time of day/week
DO: - Monitor for technical issues - Check segment quality - Document external factors
Avoid: - Peek at results and stop early - Make changes to variants - Add traffic from new sources
Looking at results before reaching sample size and stopping early leads to false positives and wrong decisions. Pre-commit to sample size and trust the process.
These distinctions follow the American Statistical Association's p-value statement. Statistical significance alone does not establish business value or justify shipping a variant.
| Result | Conclusion |
|---|---|
| Significant winner | Check effect size, uncertainty and guardrails before implementing |
| Significant loser | Keep control, learn why |
| No significant difference | Report the effect interval: it may still allow meaningful benefit and harm, or may exclude effects worth pursuing. Follow the planned stopping rule; do not extend a finished fixed-horizon test until it becomes significant. Plan a new test if needed. |
| Mixed signals | Check data quality and planned metrics; label unplanned segment findings exploratory and confirm them in a new test |
Document every test with: - Hypothesis - Variants (with screenshots) - Results (sample, metrics, significance) - Decision and learnings
For templates: See references/test-templates.md
Individual tests are valuable. A continuous experimentation program is a compounding asset. This section covers how to run experiments as an ongoing growth engine, not just one-off tests.
1. Generate hypotheses (from data, research, competitors, customer feedback)
2. Prioritize with ICE scoring
3. Design and run the test
4. Analyze results with statistical rigor
5. Promote winners to a playbook
6. Generate new hypotheses from learnings
→ Repeat
Feed your experiment backlog from multiple sources:
| Source | What to Look For |
|---|---|
| Analytics | Drop-off points, low-converting pages, underperforming segments |
| Customer research | Pain points, confusion, unmet expectations |
| Competitor analysis | Features, messaging, or UX patterns they use that you don't |
| Support tickets | Recurring questions or complaints about conversion flows |
| Heatmaps/recordings | Where users hesitate, rage-click, or abandon |
| Past experiments | "Significant loser" tests often reveal new angles to try |
Score each hypothesis 1-10 on three dimensions:
| Dimension | Question |
|---|---|
| Impact | If this works, how much will it move the primary metric? |
| Confidence | How sure are we this will work? (Based on data, not gut.) |
| Ease | How fast and cheap can we ship and measure this? |
ICE Score = (Impact + Confidence + Ease) / 3
Run highest-scoring experiments first. Re-score monthly as context changes.
Track your experimentation rate as a leading indicator of growth:
| Metric | Target |
|---|---|
| Experiments launched per month | 4-8 for most teams |
| Win rate | 20-30% is common for mature programs (sustained higher rates may indicate conservative hypotheses) |
| Average test duration | 2-4 weeks |
| Backlog depth | 20+ hypotheses queued |
| Cumulative lift | Compound gains from all winners |
When a test wins, don't just implement it — document the pattern:
## [Experiment Name]
**Date**: [date]
**Hypothesis**: [the hypothesis]
**Sample size**: [n per variant]
**Result**: [winner/loser/inconclusive] — [primary metric] changed by [X%] (95% CI: [range], p=[value])
**Guardrails**: [any guardrail metrics and their outcomes]
**Segment deltas**: [notable differences by device, segment, or cohort]
**Why it worked/failed**: [analysis]
**Pattern**: [the reusable insight — e.g., "social proof near pricing CTAs increases plan selection"]
**Apply to**: [other pages/flows where this pattern might work]
**Status**: [implemented / parked / needs follow-up test]
Over time, your playbook becomes a library of proven growth patterns specific to your product and audience.
Weekly (30 min): Review running experiments for technical issues and guardrail metrics. Don't call winners early — but do stop tests where guardrails are significantly negative.
Bi-weekly: Conclude completed experiments. Analyze results, update playbook, launch next experiment from backlog.
Monthly (1 hour): Review experiment velocity, win rate, cumulative lift. Replenish hypothesis backlog. Re-prioritize with ICE.
Quarterly: Audit the playbook. Which patterns have been applied broadly? Which winning patterns haven't been scaled yet? What areas of the funnel are under-tested?
LICENSESKILL.mdevals/evals.jsonreferences/sample-size-guide.mdreferences/test-templates.mdVendored from coreyhaines31/marketingskills, commit e85f3cbc2e4a, path skills/ab-testing, licence MIT. The upstream licence file ships inside the skill.