Skylv Code Reviewer

v1.0.4

Code Review AI Assistant. Automated code review, find potential issues and improvement suggestions. Triggers: code review, review code, code quality, code an...

0· 166·1 current·1 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for sky-lv/skylv-code-reviewer.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Skylv Code Reviewer" (sky-lv/skylv-code-reviewer) from ClawHub.
Skill page: https://clawhub.ai/sky-lv/skylv-code-reviewer
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install skylv-code-reviewer

ClawHub CLI

Package manager switcher

npx clawhub@latest install skylv-code-reviewer
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description (code review, security/performance checks, refactoring suggestions) matches the SKILL.md content. The skill declares no binaries, env vars, or config paths — which is proportionate for an instruction-only code reviewer.
Instruction Scope
SKILL.md contains only high-level instructions for reviewing pasted code (quality, security, performance, refactoring). It does not instruct reading arbitrary files, environment variables, or contacting external endpoints. Note: instructions are general/natural-language, so the agent will rely on the platform/model execution environment to perform analysis; the document does not specify privacy or telemetry behavior.
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing will be written to disk or executed as part of an installer.
Credentials
The skill requests no environment variables, credentials, or config paths. There are no apparent disproportionate secret or credential requests.
Persistence & Privilege
Flags are defaults (always: false, agent invocation allowed). The skill does not request persistent presence or modifications to other skills or system settings.
Assessment
This skill is internally coherent and doesn't request permissions or install anything. However, its source/homepage are not provided — exercise caution before pasting sensitive or proprietary code. Don't include API keys, passwords, or secrets in code you submit. If you must review sensitive code, verify your platform's data handling and retention policies first, or run a local/offline review tool instead.

Like a lobster shell, security has layers — review code before you run it.

latestvk978z9m19rcbsjtwd3g58y48ch8592zy
166downloads
0stars
5versions
Updated 1w ago
v1.0.4
MIT-0

Code Reviewer — 代码审查助手

功能说明

对代码进行全面审查,发现问题和优化机会。

使用方法

1. 代码质量检查

用户: 审查这段代码的质量:
[粘贴代码]

审查维度:

  • 代码结构
  • 命名规范
  • 注释完整性
  • 函数复杂度
  • 重复代码

2. 安全漏洞检查

用户: 检查这段代码是否有安全问题

检查项:

  • SQL注入风险
  • XSS漏洞
  • 敏感信息硬编码
  • 不安全的依赖
  • 权限控制缺失

3. 性能优化建议

用户: 这段代码有什么性能问题?如何优化?

分析项:

  • 时间复杂度
  • 空间复杂度
  • 不必要的循环
  • 数据结构选择
  • 缓存机会

4. 代码重构建议

用户: 这段代码如何重构使其更清晰?

重构方向:

  • 提取函数
  • 消除重复
  • 简化条件
  • 改善命名
  • 添加类型注解

示例输出

代码审查报告

【质量问题】
1. 函数 `processData` 过长(85行),建议拆分
   - 提取数据验证逻辑
   - 提取数据转换逻辑

2. 变量命名不清晰
   - `temp` → 建议改为 `processedResult`
   - `flag` → 建议改为 `isValidUser`

【安全问题】
⚠️ 高危:SQL查询使用字符串拼接
   第23行: `query = "SELECT * FROM users WHERE id=" + userId`
   建议:使用参数化查询

【性能问题】
1. O(n²) 嵌套循环可优化为 O(n)
   第45-52行:使用 Map 替代数组查找

2. 重复计算
   第67行:`calculateTotal()` 在循环内重复调用
   建议:提取到循环外

【优化建议】
- 添加输入验证
- 使用 TypeScript 类型注解
- 添加单元测试

支持语言

  • JavaScript / TypeScript
  • Python
  • Go
  • Java
  • C / C++
  • Rust

Comments

Loading comments...