跳到技能内容
词映 AI导航
发现工具选型指南Skills 技能AI 快讯AI图片AI视频AI文档AI办公AI助手AI搜索AI编程AI音频AI设计AI智能体模型与开发AI学习模型评测AI提示词内容检测AI金融AI 3D扫描与识别其他工具跨境电商 AI
词映 AI导航
工具库Skills 技能
我的收藏
词映 AI导航
发现工具选型指南Skills 技能AI 快讯AI图片AI视频AI文档AI办公AI助手AI搜索AI编程AI音频AI设计AI智能体模型与开发AI学习模型评测AI提示词内容检测AI金融AI 3D扫描与识别其他工具跨境电商 AI
Skills directory/DanielUsuario001/claudecode-apis-mode/code-review

Review code correctness and clarity in layers with Claude Code

Review correctness, clarity, performance, and style in order, and address severe findings before moving on.

中文

Install in Claude Code

A Claude Code workspace with the code, its intended behavior, and a reproducible input before inspecting performance or style.

  1. Review `.claude/skills/code-review/SKILL.md` and its requirements at the pinned GitHub commit.
  2. Create `.claude/skills/code-review/` in your project and save the reviewed file as `.claude/skills/code-review/SKILL.md`.
  3. Start Claude Code from that project's root, then select `/code-review` in the slash menu.

Example task

A fictional paginator uses zero-based pages. The request is `{page:0,limit:2,data:['hall','garden','loft'],actual:['garden','loft']}`. It should return the first two entries.

What to check

Lead with a correctness finding and expected `['hall','garden']`. Locate the offset error and add a page-zero regression. After resolving the severe issue, review naming, performance, and style.

Original SKILL.md on GitHub · Updated 2026-11-14

Frequently asked question

What comes first in a layered review of a pagination offset?

Record the input, expected and actual results as a correctness finding. Give a concrete fix and case to protect it before reviewing clarity and the later layers.

Browse Claude Code skills in the Chinese directory
词映 AI 导航Skills 技能
工具分类全部工具已本地化技能选型指南AI 快讯