Requesting Code Review Agent Skill
完成任务、实现重要功能或合并前使用，用于验证工作成果是否符合要求
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/jnMetaCode/superpowers-zh --skill requesting-code-reviewThe instruction itself
as written by the author请求代码审查
派遣代码审查子代理，在问题扩散之前发现它们。审查者获得的是精心组织的评估上下文——绝不是你的会话历史。这样可以让审查者专注于工作成果而非你的思考过程，同时保留你自己的上下文以便继续工作。
核心原则： 早审查，勤审查。
何时请求审查
必须审查：
- 子代理驱动开发中每个任务完成后
- 完成重要功能后
- 合并到 main 之前
可选但有价值：
- 卡住时（换个视角）
- 重构之前（建立基线）
- 修复复杂 bug 之后
如何请求
1. 获取 git SHA：
BASE_SHA=$(git rev-parse HEAD~1) # 或 origin/main
HEAD_SHA=$(git rev-parse HEAD)
2. 派遣代码审查子代理：
使用 Task 工具，指定 general-purpose 类型，填写 code-reviewer.md 中的模板
占位符说明：
{DESCRIPTION}- 你刚完成的内容简要说明{PLAN_OR_REQUIREMENTS}- 预期功能{BASE_SHA}- 起始提交{HEAD_SHA}- 结束提交
3. 处理反馈：
- Critical 问题立即修复
- Important 问题在继续之前修复
- Minor 问题记录下来稍后处理
- 如果审查者有误，用技术理由反驳
示例
[刚完成任务 2：添加验证功能]
你：让我在继续之前请求代码审查。
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[派遣代码审查子代理]
DESCRIPTION: 添加了 verifyIndex() 和 repairIndex()，支持 4 种问题类型
PLAN_OR_REQUIREMENTS: docs/superpowers/plans/deployment-plan.md 中的任务 2
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
[子代理返回]:
优点：架构清晰，测试真实
问题：
Important：缺少进度指示器
Minor：报告间隔使用了魔法数字 (100)
评估：可以继续
你：[修复进度指示器]
[继续任务 3]
与工作流的集成
子代理驱动开发：
- 每个任务完成后审查
- 在问题叠加之前发现它们
- 修复后再进入下一个任务
执行计划：
- 每个任务完成后或在自然 checkpoint 审查
- 获取反馈，应用，继续
临时开发：
- 合并前审查
- 卡住时审查
红线
绝不要：
- 因为"很简单"就跳过审查
- 忽略 Critical 问题
- 带着未修复的 Important 问题继续推进
- 对合理的技术反馈进行争辩
如果审查者有误：
- 用技术理由反驳
- 展示证明其可行的代码/测试
- 要求澄清
参见模板：requesting-code-review/code-reviewer.md
Other skills for the same job
different authors, same section of the catalogue
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
How to use it
Take jnmetacode/requesting-code-review from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.