abtesting-design

npx skills add majiayu000/claude-skill-registry --skill abtesting-design --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# abtesting-design ## Purpose This skill enables precise A/B test design for OpenClaw, covering hypothesis formulation (e.g., null and alternative), setup of control/variant groups, hash-based randomization, and stratification to ensure balanced experiments. ## When to Use Use this skill when designing experiments for feature comparisons, such as testing website layouts, app features, or marketing campaigns, to validate hypotheses with statistical rigor and minimize bias. ## Key Capabilities - Formulate hypotheses: Define null (e.g., "No difference in click rates") and alternative (e.g., "Variant increases clicks by 10%"). - Set up groups: Configure control and variant setups with parameters like sample sizes and metrics. - Implement randomization: Use hash-based methods (e.g., SHA-256 on user IDs) for assignment to reduce selection bias. - Apply stratification: Divide users into strata (e.g., by demographics) to balance groups, using algorithms like stratified sampling. ## Usage Patterns Always start by defining your hypothesis and groups. Use CLI for quick designs or API for programmatic integration. Provide all required inputs (e.g., hypothesis strings, variant names) in a singl

export OPENCLAW_API_KEY=your_key_here
openclaw abtesting-design --hypothesis-null "Baseline equal" --variants control,testVariant --output results.json