| name | jikime-marketing-ab-test |
| description | A/B testing and experimentation specialist for designing statistically valid tests, calculating sample sizes, and analyzing experiment results. |
| version | 1.0.0 |
| tags | ["marketing","ab-test","experimentation","statistics","optimization"] |
| triggers | {"keywords":["A/B test","split test","experiment","hypothesis","variant","multivariate","statistical significance","AB테스트","실험","가설"],"phases":["plan","run"],"agents":["frontend","backend","manager-strategy"],"languages":[]} |
| progressive_disclosure | {"enabled":true,"level1_tokens":"~100","level2_tokens":"~7000"} |
| user-invocable | true |
| context | fork |
| agent | general-purpose |
| allowed-tools | ["Read","Write","Edit","Bash","Grep","Glob","Task","TodoWrite"] |
A/B Test Design & Analysis
Quick Reference (30 seconds)
A/B Testing Specialist - Design tests that produce statistically valid, actionable results.
Core Principles:
- Hypothesis First: Not just "let's see what happens"
- Single Variable: Test one thing at a time
- Statistical Rigor: Pre-determine sample size, don't peek and stop early
- Business Impact: Measure what matters to the business
Key Deliverables:
- Hypothesis documentation
- Sample size calculation
- Test design specification
- Results analysis
Implementation Guide (5 minutes)
Hypothesis Framework
┌─────────────────────────────────────────────────────────────────┐
│ HYPOTHESIS TEMPLATE │
├─────────────────────────────────────────────────────────────────┤
│ Because [observation/data], │
│ we believe [change] │
│ will cause [expected outcome] │
│ for [audience]. │
│ We'll know this is true when [metrics]. │
└─────────────────────────────────────────────────────────────────┘
Weak Hypothesis:
"Changing the button color might increase clicks."
Strong Hypothesis:
"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."
Good Hypotheses Include
| Component | Description |
|---|
| Observation | What prompted this idea (data, feedback, research) |
| Change | Specific modification being tested |
| Effect | Expected outcome and direction |
| Audience | Who this applies to |
| Metric | How success will be measured |
Test Types
