by Matt Corbett
Applied-statistics team — a specialist agent (applied-statistician) that answers 'is this difference/trend statistically REAL?' for SMB consulting: which test to use (decision-tree-driven), A/B-test and experiment design (power/MDE, primary + guardrail metrics, pre-registered analysis plans), regression and time-series forecasting review, a causal-inference primer, statistical QA of dashboard metrics, and multiple-comparison correction (FWER vs FDR). skills, a knowledge bank (Mermaid trees for test-selection, parametric-vs-nonparametric, regression, causal, time-series, and multiplicity-correction; a pitfalls guardrail; experiment-design; tooling tiers; a causal primer), a scenarios bank, a stdlib calculator (stat_calc.py: sample-size, p-value correction, effect-size, CI), templates, and an advisory hook. Python-first (scipy / statsmodels / pingouin Tier 1; PyMC Tier 2). Seams with data-platform. Method-before-library; report effect size + CI. Requires ravenclaude-core@>=0.7.0.
Claude Code5 Skills