engineering excellent

Review Judge

Evaluate AI or human code review comments against actual repository code, tests, diffs, call sites, and project conventions. Use when the user asks whether review suggestions, MR comments, IDE AI comments, or code-review feedback are valid, worth accepting, should be rejected, or need ROI-based triage.

Agent 安装命令

先 dry-run 再安装；仓库需已公开，或 Agent 需具备访问权限。

git clone https://github.com/yupeng0512/cursor-skills.git ~/.skillhub/yupeng-cursor-skills
cd ~/.skillhub/yupeng-cursor-skills
./install.sh --target codex --skill review-judge --dry-run
./install.sh --target codex --skill review-judge
~/.local/bin/skillhub-yupeng doctor --target codex --json

claude

--target claude

codex

--target codex

cursor

--target cursor

Agent 安装命令

标签