4 级 LLM-as-Judge spec 合规判定。T 阶段官方 /code-review 做广度扫描后, 本 skill 做 design.md spec 深度合规。
Scanned 9/5/2026
Install to Claude Code
npx -y skills add WenJunDuan/Rlues --skill code-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Code Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wenjunduan-code-review-d6d77c10)More formats (shields.io, HTML) on the badges page.
---
name: code-review
description: 4 级 LLM-as-Judge spec 合规判定。T 阶段官方 /code-review 做广度扫描后, 本 skill 做 design.md spec 深度合规。
---
# Code Review — LLM-as-Judge
与官方 `/code-review` 分工:
- 官方: 4 parallel agents 扫 bugs + compliance + git blame
- 本 skill: 对标 design.md spec, 输出 4 级判定
## Spec 合规清单
1. 每个 MUST 需求是否实现?
2. 每个源码文件有对应测试?
3. 边界: 空输入/超长/并发/错误路径?
4. 安全: 无硬编码密钥, 输入已验证
5. 可读: 函数 < 50 行, 注释说 WHY, 严格类型
6. 简洁: 无过度工程, 无重复, 无空 catch
## 输出
```json
{"level": "PASS|CONCERNS|REWORK|FAIL", "issues": [...], "summary": "..."}
```
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!