R Analysis Reviewer — Data & AI agent for Claude Code
Reviews R analysis code, Rmd and qmd files for silent wrong results — joins that drop rows, type coercion, non-deterministic output, and conclusions that outrun the data.
How to install R Analysis Reviewer
Installs to ~/.claude/agents/jflournoy-claude-analysis-config-r-analysis-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/jflournoy/claude-analysis-config/HEAD/agents/r-analysis-reviewer.md -o ~/.claude/agents/jflournoy-claude-analysis-config-r-analysis-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What R Analysis Reviewer does
name: r-analysis-reviewer description: Reviews R analysis code, Rmd and qmd files for silent wrong results — joins that drop rows, type coercion, non-deterministic output, and conclusions that outrun the data. Fires automatically on .R/.Rmd/.qmd edits. Reports findings; never edits. tools: Read, Grep, Glob, Bash model: sonnet
You review R analysis code. The output of this work is published numbers, so your concern is not whether the script runs — it does — but whether the number it prin
Alternatives in Data & AI
- Review Code Correctness — A code review agent that checks analysis scripts for logical errors, incorrect function usage, wrong variable 134 ★
- Geo AI Scorer — Use only for an explicitly requested experimental content-quality review alongside the deterministic geoptimiz 81 ★
- Add Task Type — Adds a new AI task type to the woolball server: endpoint, handler, preprocessing route, logic class, DI regist 66 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Harness AI Dev
AI engineer — LLM and agent features, prompts, model integration, tool definitions, retrieval, and the evals t
Filter Tuner
Looks at what the deterministic filter and the AI scoring kept or rejected, finds the rules that let bad offer
Admin Portal Architect
Use when auditing the admin console/back-office: which pages actually work, silent empty results, dead routes,
AI Output Reviewer
Read-only reviewer for AI/LLM integration in the forgeward gate. Fires ONLY when the diff adds or modifies a c
Noemeo AI Engineer
Designs and builds model-backed components in Noemeo repos -- deciding between deterministic code, classical M
Data Eng Reviewer
Data-engineering expert for the code-review panel. Spawned when the diff touches SQL, dbt models or schema .ym
Related Skills
Claude Short Answer Skill
Initiate with /short - A Claude Code skill that switches output to summary-only mode - cutting reasoning, walk
Debug Blitz
Parallel debug assault — fires debug-detective + silent-failure-hunter + env-debugger simultaneously. Three ro
Reconcile Tasks
Bounded, schedulable reconciler that fixes issues sitting in the wrong state against a fixed, enumerated rule