mcpField
R
review-r

review-r

github.com/pedrohcgsTesting & quality1.7k58 installsUpdated 4w ago
Repository

About review-r

review-r is a skill for reviewing R scripts with the r-reviewer agent. It produces per-script findings and severity summaries while leaving source files unchanged.

Key features

  1. 01Select files by filename, lecture, or directory
  2. 02Invoke the r-reviewer agent
  3. 03Summarize issue counts by severity
  4. 04Keep R source files unchanged

Use cases

  1. 01Review one R script before sharing it
  2. 02Audit scripts for a particular lecture
  3. 03Generate findings across the R script directories

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/pedrohcgs/claude-code-my-workflow --skill review-r

After installing, type/review-rin Claude Code to confirm it loaded.

Details

From the project README

Review R Scripts

Run the comprehensive R code review protocol.

Steps

  1. Identify scripts to review:

    • If $ARGUMENTS is a specific .R filename: review that file only
    • If $ARGUMENTS is LectureN: review all R scripts matching that lecture
    • If $ARGUMENTS is all: review all R scripts in scripts/R/ and Figures/*/

  2. 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
    • Return its report as its final response (ending with the findings json block); this skill saves it to quality_reports/[script_name]_r_review.md — the agent is read-only

  3. After all reviews complete, present a summary:

    • Total issues found per script
    • Breakdown by severity (Critical / High / Medium / Low)
    • Top 3 most critical issues

  4. Leave the R source files unchanged — the report goes to the user, who decides what to fix. Only produce reports. Fixes are applied after user review.

Comments

Markdown supported