Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

review-r

Estrellas0

Forks0

Actualizado12 de febrero de 2026, 10:47

Run the R code review protocol on R scripts. Checks code quality, reproducibility, data.table conventions, domain correctness, and professional standards. Produces a report without editing files.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

coadywing

coadywing/T32_oneill

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Analistas de garantía de calidad de software y probadoresOcupaciones informáticas y matemáticas·SOC 15-1253

SKILL.md

readonly

name	review-r
description	Run the R code review protocol on R scripts. Checks code quality, reproducibility, data.table conventions, domain correctness, and professional standards. Produces a report without editing files.
disable-model-invocation	true
argument-hint	[filename or 'all']

Review R Scripts

Run the comprehensive R code review protocol.

Steps

Identify scripts to review:
- If $ARGUMENTS is a specific .r filename: review that file only
- If $ARGUMENTS is all: review all R scripts in code/
For each script, launch the r-reviewer agent with instructions to:
- Follow the full protocol in the agent instructions
- Read .claude/rules/r-code-conventions.md for current standards
- Save report to quality_reports/[script_name]_r_review.md
After all reviews complete, present a summary:
- Total issues found per script
- Breakdown by severity (Critical / High / Medium / Low)
- Top 3 most critical issues
IMPORTANT: Do NOT edit any R source files. Only produce reports. Fixes are applied after user review.

Más de este repositorio

mismo repositorio

convert-proposal

coadywing/T32_oneill

Build the T32 grant proposal as PDF and/or Word. Supports full build, Word-only, PDF-only, or single-section Word export for collaborator review.

2026-02-120

review-grant

coadywing/T32_oneill

Full grant review pipeline — runs compliance checker, study section reviewer, and proofreader on the T32 proposal. Aggregates all results into a single summary report.

2026-02-120

compile-paper

coadywing/T32_oneill

Compile the LaTeX manuscript. Runs latexmk (or multi-pass pdflatex + biber) from the project root and reports errors, warnings, and undefined references.

2026-02-120

devils-advocate

coadywing/T32_oneill

Challenge academic content with 5-7 specific pedagogical questions. Checks ordering, prerequisites, gaps, alternatives, notation conflicts, cognitive load, and standalone readiness. Works on slides, lecture notes, paper drafts, and assignments.

2026-02-120

pedagogy-review

coadywing/T32_oneill

Run holistic pedagogical review on teaching materials — slides, lecture notes, assignments, or syllabi. Checks narrative arc, prerequisites, worked examples, notation clarity, and pacing.

2026-02-120

proofread

coadywing/T32_oneill

Run the proofreading protocol on project files. Checks grammar, typos, overflow, consistency, and academic writing quality. Produces a report without editing files.

2026-02-120

name	review-r
description	Run the R code review protocol on R scripts. Checks code quality, reproducibility, data.table conventions, domain correctness, and professional standards. Produces a report without editing files.
disable-model-invocation	true
argument-hint	[filename or 'all']

Review R Scripts

Run the comprehensive R code review protocol.

Steps

Identify scripts to review:
- If $ARGUMENTS is a specific .r filename: review that file only
- If $ARGUMENTS is all: review all R scripts in code/
For each script, launch the r-reviewer agent with instructions to:
- Follow the full protocol in the agent instructions
- Read .claude/rules/r-code-conventions.md for current standards
- Save report to quality_reports/[script_name]_r_review.md
After all reviews complete, present a summary:
- Total issues found per script
- Breakdown by severity (Critical / High / Medium / Low)
- Top 3 most critical issues
IMPORTANT: Do NOT edit any R source files. Only produce reports. Fixes are applied after user review.