review-r
Skill8 starsChanged 4 months agoMITView on GitHub
R code review on existing scripts. Checks quality, reproducibility, domain correctness, professional standards. Produces report without editing files. Use when evaluating or auditing existing R code, not writing new analysis.
3 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- pedrohcgs/claude-code-my-workflowedited, first seen Nov 7, 2026
- maxwell2732/paper-replicate-agent-demoedited, first seen Feb 21, 2026
- luischanci/claude-code-research-startertheir own version, first seen Feb 13, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- pedrohcgs/claude-code-my-workflow★ 1.7k36% same
- maxwell2732/paper-replicate-agent-demo★ 13464% same
Wrote their own version · 1
- luischanci/claude-code-research-starter★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- data-analysisSkill
- data-finderSkill
- lit-reviewSkill
- new-projectSkill
- proofreadSkill
- quality-gateSkill
- research-setupSkill
- review-paperSkill
- revise-paperSkill
- session-logSkill
- validate-bibSkill
- write-paperSkill
The file
We split this skill into the rules it gives an agent
8 rules. 3 are common, 0 are distinctive, and 5 are very specific to this project.
3
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 11
Run the comprehensive R code review protocol.
- Very specific: line 16
If $ARGUMENTS is a specific .R filename: review that file only
- Very specific: line 17
If $ARGUMENTS is a name pattern (e.g., model_name): glob for matching .R files.
- Very specific: line 22
If $ARGUMENTS is all: review all R scripts in scripts/R/ and Figures/*/
- Very specific: line 23
If $ARGUMENTS is empty, glob for all .R files.
- Common: line 26
Follow the full protocol in the agent instructions
- Very specific: line 27
Read ${CLAUDE_PLUGIN_ROOT}/rules/r-code-conventions.md for current standards
- Common: line 36
Only produce reports. Fixes are applied after user review.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review R Scripts
Run the comprehensive R code review protocol.
Steps
- Identify scripts to review:
- If
$ARGUMENTSis a specific.Rfilename: review that file only - If
$ARGUMENTSis a name pattern (e.g.,model_name): glob for matching.Rfiles. If multiple matches, use AskUserQuestion:- header: "Scripts"
- question: "Multiple R scripts match that pattern. Which should I review?"
- multiSelect: true
- options: list up to 4 matched files (label: filename, description: path and last modified). User can select multiple.
- If
$ARGUMENTSisall: review all R scripts inscripts/R/andFigures/*/ - If
$ARGUMENTSis empty, glob for all.Rfiles. If multiple found, use AskUserQuestion as above.
- If
- For each script, launch the
r-revieweragent with instructions to:- Follow the full protocol in the agent instructions
- Read
${CLAUDE_PLUGIN_ROOT}/rules/r-code-conventions.mdfor 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

