Experiment Designer
Design statistically valid experiments with hypothesis testing and sample size calculations
What You Can Do
You can design experiments that meet statistical validity standards by defining clear null and alternative hypotheses, calculating required sample sizes based on effect sizes and power, identifying confounding variables to control, and pre-specifying analysis plans that prevent p-hacking and bias. This skill produces complete experiment designs combining scientific rigor with practical feasibility for product testing, marketing validation, and research studies.
Features
creates null and alternative hypotheses with clear statistical framing
determines required participants using effect size, power, and significance levels
maps variables that could bias results and specifies control methods
designs assignment schemes that ensure unbiased group allocation
structures primary and secondary outcomes before data collection to prevent selective reporting
justifies sample sizes and provides confidence in effect detection
estimates execution timeline and required resources for feasibility assessment
Example Output
Example 1: Product A/B Test
- Hypothesis: Adding social proof to checkout increases conversion by 8% (effect size)
- Sample size: 2,400 users per variant (n=4,800 total) to achieve 80% power at 5% significance
- Confounders controlled: device type, traffic source, time of day
- Primary metric: Checkout completion rate; Secondary: revenue per user
- Timeline: 2-week test window
Example 2: Marketing Campaign Study
- Null hypothesis: Email subject line A and B have equal open rates
- Calculation: 6,500 recipients per variant to detect 2% lift with 90% power
- Randomization: Random split at subscriber level, stratified by engagement tier
- Analysis plan: Chi-square test on primary outcome; subgroup analysis by user tenure as pre-specified secondary outcome
What's Included
- SKILL.md instruction file with full experiment design methodology:
- Hypothesis statement template: structured format for null/alternative hypotheses with effect size specifications
- Sample size calculation worksheet: interactive framework with power, significance, and effect size inputs
- Confounder control checklist: systematic list of variables to identify and control strategies by experiment type
- Pre-analysis plan template: captures hypotheses, metrics, subgroups, and analysis procedures before data collection
- Power analysis documentation guide: explains trade-offs between sample size, power, and effect magnitude
Who It's For
- Product managers — designing A/B tests for feature launches and user experience optimization
- Research scientists — planning rigorous studies with statistical validity and reproducibility
- Data scientists — structuring experiments that prevent bias and support causal inference
- Marketing analysts — validating campaign strategies with appropriate sample sizes and controls
- UX researchers — designing behavioral experiments with confounding variable management
Best For
- A/B tests for product features, checkout flows, and user interface changes
- Marketing campaign validation and channel comparison studies
- Randomized controlled trials and quasi-experimental designs
- Sample size justification for funding applications and research proposals
- Pre-analysis plan documentation for open science and reproducibility standards
You might also like
You can structure and run Kaizen events from start to finish, guiding your team through waste analysis, root-cause identification, and rapid improvement design. The skill generates detailed event agendas, countermeasure documentation, and performance metrics—enabling you to close improvement opportunities within days rather than weeks.
by kylezantos
Transform raw manufacturing P&L data into actionable insights by automatically identifying cost variances, pinpointing root causes, and generating executive-ready narratives. You upload your plant's P&L statement, provide context about recent operational changes, and Claude analyzes the numbers to explain why costs moved and what actions drive profitability.
by kylezantos
This skill systematically analyzes out-of-spec chemical manufacturing batches to identify root causes and recommend parameter adjustments. You provide process data, operating conditions, and quality metrics; Claude performs hypothesis testing, statistical correlation analysis, and multi-variate optimization to pinpoint the failure mechanism. You get actionable recommendations ranked by impact and implementation risk.
by kylezantos
You can leverage Claude to streamline every aspect of film production coordination—from managing crew schedules and budgets to troubleshooting on-set logistics and creative challenges. This skill helps you create call sheets, coordinate locations, track production expenses, and quickly solve problems that arise during shooting without disrupting your workflow.
by kylezantos
You provide production data and process details, and this skill systematically analyzes the information to identify root causes of quality issues, yield losses, or equipment failures. It develops prioritized corrective actions with implementation timelines, compliance documentation, and performance metrics to track improvement effectiveness.
by kylezantos
This skill systematically analyzes your production data using proven continuous improvement methodologies like Lean and Six Sigma to identify bottlenecks, root causes, and measurable improvement opportunities. You'll receive prioritized, actionable recommendations with implementation roadmaps and risk assessments that help you focus on high-impact optimizations driving real cost savings and efficiency gains.
by kylezantos
Accelerate literature reviews by automatically synthesizing research papers, extracting key methodologies and findings, and identifying research gaps. This skill analyzes multiple papers simultaneously to spot unexplored areas, methodological blind spots, and emerging opportunities in your field. You'll get structured analysis, comparison matrices, and research landscape summaries that would normally take weeks to produce manually.
Prepare comprehensive audit documentation, track non-conformance issues from identification through resolution, and generate corrective action plans. You can document audit findings, prioritize risks by severity, assign accountability, and create formal reports that demonstrate compliance readiness to auditors and stakeholders.
by kylezantos