# Code Review

> >

- **Type:** Skill
- **Install:** `agentstack add skill-zhouyinlong-lab-dog-skills-code-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ZhouYinLong-lab](https://agentstack.voostack.com/s/zhouyinlong-lab)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ZhouYinLong-lab](https://github.com/ZhouYinLong-lab)
- **Source:** https://github.com/ZhouYinLong-lab/Dog-Skills/tree/main/code-review

## Install

```sh
agentstack add skill-zhouyinlong-lab-dog-skills-code-review
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Code Review — 双模式代码审查元技能

> 两种互补的审查模式：standard 把关工程质量，adversarial 模拟攻击者视角。覆盖从常规 PR 到安全审计的完整审查链路。

## 两种模式

```
┌──────────────────────────────────────────────────────────────┐
│                    Code Review                                 │
│                                                               │
│  /review standard     ── 五维工程质量审查                      │
│  /review adversarial  ── 恶意用户视角破坏性测试                │
└──────────────────────────────────────────────────────────────┘
```

---

## Standard 模式 — 五维工程质量审查

5 个 Agent 并行审查 + 置信度过滤：

```
代码 → 安全Agent · 性能Agent · 可维护Agent · 规范Agent · 边界Agent
         │
         ▼
    置信度过滤（自动剔除假阳性）
         │
         ▼
    Critical → High → Medium → Low 分级报告
```

**何时用**：日常 PR、提交前检查、重构后验证。

---

## Adversarial 模式 — 对抗式审查

AI 换一个身份，从"我要用各种奇怪的数据搞崩你的系统"出发：

```
恶意用户视角 → 多Agent并发扫描
    │
    ├── 逻辑漏洞："这个判断条件有没有反例？"
    ├── 安全风险："注入/XSS/权限绕过？"
    ├── 边界条件："传null/负数/超大值会怎样？"
    ├── 隐藏Bug："并发/竞态/死锁？"
    └── 思维盲点："你没想到什么？"
```

**何时用**：安全审计、核心模块上线前、被攻击后的排查。

---

## 使用方式

| 你说 | 模式 |
|------|------|
| "帮我审查代码" / `/code-review` | Standard（默认） |
| "审查 PR 的代码质量" | Standard |
| "帮我做对抗式审查" / "以攻击者视角审查" | Adversarial |
| "全面审计——先 standard 再 adversarial" | 双模式串联 |

---

## 推荐流水线

```
Code Simplifier（先优化结构）
       │
       ▼
Code Review standard（工程质量把关）
       │
       ▼
Code Review adversarial（安全+边界兜底）
       │
       ▼
人工 Review
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ZhouYinLong-lab](https://github.com/ZhouYinLong-lab)
- **Source:** [ZhouYinLong-lab/Dog-Skills](https://github.com/ZhouYinLong-lab/Dog-Skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-zhouyinlong-lab-dog-skills-code-review
- Seller: https://agentstack.voostack.com/s/zhouyinlong-lab
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.