Growth Experiment Design & Analysis
Design and analyze growth experiments with statistical rigor and actionable insights
What You Can Do
You can design hypothesis-driven A/B tests and multivariate experiments from scratch, complete with control group setup and success metric definition. Claude analyzes experimental results using statistical methods to determine significance, confidence levels, and effect sizes. You generate data-driven growth roadmaps and prioritize initiatives based on experiment learnings and metric correlations.
Features
Define clear hypotheses, control/variant groups, sample sizes, and success metrics for controlled experiments
Calculate p-values, confidence intervals, and effect sizes to determine if results are statistically valid
Transform raw experiment data into actionable insights with uplift calculations and business implications
Rank growth initiatives by expected impact, resource requirements, and confidence levels from experimental data
Create testable hypotheses based on funnel analysis, user behavior patterns, and data anomalies
Design complex experiments with multiple variables and analyze interaction effects between factors
Determine required sample sizes based on baseline metrics, desired uplift, and statistical power
Example Output
Example 1: A/B Test Analysis You provide: Control (8,500 impressions, 425 conversions) vs. Variant (8,200 impressions, 520 conversions)
Claude outputs:
- Conversion rates: 5.0% (control) vs. 6.3% (variant) = 26% uplift
- Statistical significance: p < 0.01 (>99% confidence)
- Recommendation: ✅ Launch variant — high confidence, low risk
Example 2: Growth Experiment Design You ask: "Design an experiment to improve free trial conversion"
Claude generates:
- Hypothesis: Removing credit card requirement increases trial-to-paid conversion by 8%
- Control: Current funnel (card required)
- Variant: Skip card, collect at conversion decision
- Metrics: Trial signup rate, trial-to-paid rate, churn
- Sample size: 5,000 per arm (28-day test)
- Risk factors: Chargebacks, fraud patterns
Example 3: Growth Roadmap You submit: Recent experiments on onboarding, pricing tiers, and referral bonuses
Claude prioritizes:
- Referral bonus expansion (45% expected impact, low cost, proven by experiments)
- Pricing tier optimization (18% impact, medium effort, high confidence)
- Advanced onboarding flow (12% impact, high cost, moderate confidence)
What's Included
- Hypothesis Framework: Structured template for defining clear, testable hypotheses with expected outcomes and assumptions
- A/B Test Planning Toolkit: Complete checklist for designing experiments: control definition, variant specification, sample sizing, timeline
- Statistical Analysis Guide: Step-by-step methods for calculating significance, confidence intervals, and effect sizes from experiment data
- Growth Metrics Framework: How to select, define, and track primary/secondary metrics aligned with business objectives
- Experiment Playbook: Pre-built templates for common growth experiments: viral loops, pricing changes, feature rollouts, UX optimizations
Who It's For
- Growth Manager
- Product Manager
- Data Analyst
- Startup Founder
- Conversion Rate Optimizer
Best For
- Designing A/B tests and multivariate experiments
- Analyzing experimental results with statistical confidence
- Prioritizing growth initiatives based on data
- Creating hypothesis-driven growth roadmaps
- Calculating sample sizes and experiment timelines
You might also like
You can transform disparate consumer signals—purchase behavior, social engagement, demographic shifts, and psychological motivations—into coherent trend narratives with actionable forecasting insights. This skill focuses on the why behind behavior rather than surface aesthetics, helping you identify inflection points where consumer preferences are shifting, validate collection strategy against actual psychology, and build predictive consumer profiles for 6-18 month forecasting horizons.
by er1chu
This skill helps you design statistically rigorous experiments, calculate exact sample sizes based on your confidence and power requirements, and interpret results with confidence intervals and significance testing. You'll move beyond guesswork to measure what actually drives growth. It provides frameworks for hypothesis formation, experiment design, result interpretation, and prioritizing your experiment backlog by expected impact and effort.
by oysteinkrog
You can systematically synthesize signals from multiple fashion sources—runway shows, street style, consumer behavior, fabric innovations, and cultural movements—to identify which silhouette changes will gain traction in upcoming seasons. This skill accelerates the analytical process by organizing observations into structured forecasting frameworks that help you spot inflection points where silhouette preferences shift, enabling you to develop product roadmaps and communicate trend reasoning to design teams and merchandisers with data-backed justification.
by er1chu
You can rapidly identify emerging color trends by processing competitive intelligence, social media sentiment, runway analysis, and cultural indicators into structured forecasts. Claude helps you validate pattern strength across multiple data sources and build defensible color recommendations backed by cultural movements, consumer psychology, and market performance—enabling you to justify palette choices to executives and design teams with 6-18 month lead time.
by er1chu
This skill systematically searches your vault and Slack across specified time ranges to identify decisions using natural language patterns. It extracts decision context—including rationale, participants, dates, and sources—then matches decisions to projects and identifies gaps in your Decision Logs. You get a curated list of decisions that should be documented, reducing the risk of losing critical project decisions in the noise of daily communications.
by er1chu
You'll transform raw consumer research, social listening, and feedback into actionable trend intelligence by decoding what consumers are actually thinking, feeling, and planning to do. This skill creates a standardized framework for interpreting sentiment data that reveals behavioral intention, emotional drivers, and adoption velocity—enabling you to spot emerging opportunities and category momentum shifts before they're visible to competitors.
by er1chu
This skill stress-tests your pitch narrative by analyzing story structure, identifying investor objections before they arise, and ensuring your message stays coherent across all deck sections. You'll get targeted feedback on narrative strength, compelling counterarguments to anticipated concerns, and audience-specific messaging variants that resonate with different investor profiles.
by er1chu
You can strengthen your pitch narrative by tailoring messaging to specific investor types, identifying and preparing responses to likely objections, and practicing delivery with detailed feedback. This skill helps you transform a good pitch into a compelling one by analyzing your deck's structure, clarity, and persuasive impact.
by er1chu