UiPath

Coder Eval Review — Productivity skill for Claude Code

Productivity community

Generate per-task review.json (summary + tags) for a completed run.

How to install Coder Eval Review

Installs to ~/.claude/commands/uipath-coder_eval-coder-eval-review.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/UiPath/coder_eval/HEAD/.claude/commands/coder-eval-review.md -o ~/.claude/commands/uipath-coder_eval-coder-eval-review.md

Restart Claude Code, or start a new session, for it to be picked up.

What Coder Eval Review does

allowed-tools: Read(), Glob(), Grep(), Bash(ls:), Bash(jq:), Bash(python3:), Write(runs/*) description: Generate per-task review.json (summary + tags) for a completed run

Context

If `$ARGUMENTS` is empty or blank, resolve the run to review per the "No target given" rule in `.claude/shared/run-layout.md` — discover the run root, then take `latest` if that symlink resolves and the newest run directory by name if it does not. Tell the user which run you picked and how you got the

Alternatives in Productivity

Reviews Plans — Review all active architecture plans relevant to the current task 15.6k ★
Trio — Force a trio review of the task that follows — pm, designer, and engineer weigh in in parallel before any acti 324 ★
Huashu Weread — 微信读书高阶顾问 · 在官方 weread skill 之上加一层「读书顾问的工作流」· 书架+笔记交叉分析 · 4 个 workflow (advisor/path/alchemy/review) · Made by 140 ★