Aso ab testing
Skill FelixGraeber/claude-aso-audit-skill/skills/aso-ab-testing
ASO audit skill pack for Claude Code: audit App Store and Google Play listings, keywords, metadata, visuals, reviews, and competitors.
npx -y skills add FelixGraeber/claude-aso-audit-skill --skill aso-ab-testingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
A/B testing strategy for iOS Product Page Optimization (PPO) and Android Store Listing Experiments. Hypothesis design, variant creation, statistical significance guidance. Triggers on: "A/B test", "experiment", "PPO", "product page optimization", "store listing experiments".
SKILL.md
3.0 KB, as published. Nobody here has run it
ASO A/B Testing — Experimentation
Capabilities
- Test hypothesis generation from audit findings
- Platform-specific experiment design
- Variant recommendations (control vs treatment)
- Statistical significance and duration guidance
- Results interpretation framework
- Sequential test roadmap planning
Platform Capabilities
iOS: Product Page Optimization (PPO)
| Aspect | Specification |
|---|---|
| Testable elements | App icon, screenshots, app preview video |
| NOT testable | Title, subtitle, keywords, description |
| Max treatments | 3 (plus original) |
| Traffic split | Apple-controlled |
| Min duration | 7 days recommended |
| Max duration | 90 days |
| Audience | All users or specific locales |
| Active tests | 1 at a time (on default product page) |
Android: Store Listing Experiments
| Aspect | Specification |
|---|---|
| Testable elements | Icon, feature graphic, screenshots, short description, full description, promo video |
| Max experiments | 5 localized + 1 main simultaneously |
| Traffic split | Configurable |
| Min duration | 7 days recommended |
| Audience | Default or country-specific listings |
Test Design Framework
1. Hypothesis
State: "Changing [element] from [current] to [proposed] will [increase/decrease] [metric] because [reason]."
2. Element Selection (priority order)
- Screenshots (highest conversion impact, testable on both platforms)
- App icon (affects browse + search impressions)
- Short description / feature graphic (Android only for text)
- Preview video (presence vs absence)
3. Variant Design
- Change ONE element per test (isolate variable)
- Make the change meaningful (not subtle)
- Have clear visual/copy difference between control and treatment
4. Duration & Sample Size
- Minimum 7 days (capture weekday + weekend patterns)
- Need 90%+ confidence level
- Rule of thumb: ~1000 page views per variant for meaningful results
- Account for seasonal effects
5. Success Metrics
- Primary: Install conversion rate (page view → install)
- Secondary: First-time installers, 1-day retention (Android)
Output Format
# A/B Test Plan: [App Name]
## Test 1: [Element Being Tested]
- Hypothesis: [statement]
- Platform: iOS PPO / Android Experiment
- Control: [current element description]
- Treatment: [proposed change]
- Expected impact: [conversion increase estimate]
- Duration: [recommended days]
- Success criteria: [metric + threshold]
## Test Roadmap (Sequential)
1. [highest impact test first]
2. [second test]
3. [third test]
Available Tools
Read, Bash, Write, Glob, Grep