Menu
Review existing R analysis code for quality and reproducibility.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
End-to-end empirical data analysis workflow for R or Python projects.
Find and assess datasets for a research question.
Repository-wide consistency audit for skills, hooks, rules, and docs.
Systematic literature review workflow using parallel librarian agents.
Structured interview and project-spec workflow for new research ideas.
Proofreading workflow for academic manuscripts and papers.
| name | review-r |
| description | Review existing R analysis code for quality and reproducibility. |
Run the comprehensive R code review protocol.
Identify scripts to review:
$ARGUMENTS is a specific .R filename: review that file only$ARGUMENTS is a name pattern (e.g., model_name): glob for matching .R files. If multiple matches, ask the user to choose conversationally. Do not use request_user_input here because the selection may be multi-file and Codex question UI is single-choice only.$ARGUMENTS is all: review all R scripts in scripts/R/ and Figures/*/$ARGUMENTS is empty, glob for all .R files. If multiple are found, ask the user to choose conversationally as above.For each script, read agents/r-reviewer.md and apply that review protocol.
rules/r-code-conventions.md for current standardsquality_reports/ if it is missing before savingquality_reports/[script_name]_r_review.mdr-reviewer as a separate subagent and merge the resultAfter all reviews complete, present a summary:
IMPORTANT: Do NOT edit any R source files. Only produce reports. Fixes are applied after user review.