← Back to Skills Marketplace
tlreal

code-review

by tlreal · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
841
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install code-review1
Description
在代码提交前或任务完成后使用,进行代码审查
README (SKILL.md)

\r \r

Code Review - 代码审查\r

\r

概述\r

\r 系统性地审查代码变更,确保质量、可维护性和正确性。\r \r

审查维度\r

\r

1. 正确性\r

\r

  • 逻辑是否正确?\r
  • 边界情况是否处理?\r
  • 错误处理是否完整?\r \r

2. 可读性\r

\r

  • 命名是否清晰?\r
  • 代码结构是否清晰?\r
  • 注释是否有帮助(不是噪音)?\r \r

3. 可维护性\r

\r

  • 是否遵循 DRY 原则?\r
  • 是否容易修改和扩展?\r
  • 依赖是否合理?\r \r

4. 测试\r

\r

  • 测试覆盖是否充分?\r
  • 测试是否有意义?\r
  • 测试是否可读?\r \r

问题分级\r

\r | 级别 | 含义 | 处理 |\r |------|------|------|\r | Critical | 必须修复才能合并 | 阻塞 |\r | Important | 应该修复 | 建议修复 |\r | Minor | 可以改进 | 可选 |\r | Nitpick | 个人偏好 | 仅供参考 |\r \r

审查输出格式\r

\r

## 代码审查报告\r
\r
### 概览\r
- 变更: [简述变更内容]\r
- 审查者: AI\r
- 日期: YYYY-MM-DD\r
\r
### 问题\r
\r
#### Critical\r
- [ ] **文件:行号** - 问题描述\r
\r
#### Important  \r
- [ ] **文件:行号** - 问题描述\r
\r
#### Minor\r
- [ ] **文件:行号** - 问题描述\r
\r
### 优点\r
- [列出代码的优点]\r
\r
### 结论\r
[通过/需要修改后通过/不通过]\r
```\r
\r
## 嵌入式领域扩展\r
\r
**额外检查项:**\r
- 内存分配是否安全?\r
- 是否有资源泄漏风险?\r
- 中断上下文是否正确使用?\r
- 时序要求是否满足?\r
- 功耗影响是否考虑?\r
Usage Guidance
This skill is internally consistent and low-risk: it only provides review guidelines and a report template and asks for nothing from your system. Before using: (1) avoid pasting sensitive secrets or proprietary code into the chat — provide minimal, non-sensitive snippets or a sanitized diff; (2) if you don't want the agent to invoke this skill autonomously, keep it user-invocable only or change agent policies; (3) if you plan to feed repository links, ensure the agent has only the access you intend (do not expose credentials). Overall it appears safe to install, but treat any shared source code as sensitive data and review organizational policies first.
Capability Analysis
Type: OpenClaw Skill Name: code-review1 Version: 1.0.0 The skill bundle provides a standard framework for performing code reviews, outlining dimensions such as correctness, readability, and maintainability. The instructions in SKILL.md are well-structured and aligned with the stated purpose, including specific considerations for embedded systems, with no evidence of malicious intent, data exfiltration, or unauthorized command execution.
Capability Assessment
Purpose & Capability
Name/description (
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install code-review1
  3. After installation, invoke the skill by name or use /code-review1
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Major change: Simplified and fully localized the code review skill, removing the previous detailed, English-language checklists and process documentation. - README.md file has been removed. - SKILL.md now uses a concise, Chinese-language structure with essential review dimensions, severity levels, basic output format, and embedded systems extensions. - The new version is easier to understand and apply for Chinese-speaking users, focusing on core review principles.
Metadata
Slug code-review1
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is code-review?

在代码提交前或任务完成后使用,进行代码审查. It is an AI Agent Skill for Claude Code / OpenClaw, with 841 downloads so far.

How do I install code-review?

Run "/install code-review1" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is code-review free?

Yes, code-review is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does code-review support?

code-review is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created code-review?

It is built and maintained by tlreal (@tlreal); the current version is v1.0.0.

💬 Comments