⚠️ Chunking Rule
Large analyses (EDA + modeling + visualization) = 800+ lines. Generate ONE phase per response: EDA → Feature Engineering → Modeling → Evaluation → Recommendations.
Statistical modeling - A/B testing, causal inference, customer analytics (CLV, churn), time series forecasting. Use for business analytics or experiment design.
npx skillmds@latest add zangxin75/data-scientist Large analyses (EDA + modeling + visualization) = 800+ lines. Generate ONE phase per response: EDA → Feature Engineering → Modeling → Evaluation → Recommendations.
zangxin75/openclaw-skills/tree/main/sw-data-scientist commit 75a9965e03