useful

Review code written by Claude Code or humans across multiple languages. Use when asked to review, audit, critique, or analyze code quality. Supports R, Python, SQL, C++, Rust, Go, Ansible, Kustomize/Kubernetes, Dockerfiles, Docker Compose, and Bash. Covers correctness, security, performance, testing, documentation, and architecture. Produces actionable output for Claude Code to fix issues plus human-readable REVIEW.md summaries.

R-first data science and statistical analysis with SQL as secondary language. Use when the user asks to analyze data in R, write R scripts, create tidyverse pipelines, build statistical models, work with time series (fable/tsibble), run machine learning workflows (tidymodels), query databases from R (DuckDB, dbplyr), build reproducible pipelines (targets), or parallelize computations (crew/mirai). Triggers on R, tidyverse, dplyr, ggplot2, targets, tidymodels, DuckDB, time series forecasting, or statistical modeling requests.