Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
jnmetacode avatar

Requesting Code Review

  • 851 installs
  • 7.5k repo stars
  • Updated July 31, 2026
  • jnmetacode/superpowers-zh

requesting-code-review is a Claude Code skill that dispatches an independent code-review sub-agent with clean git SHAs and requirements context for developers who need objective validation before merging important work.

About

requesting-code-review is a Superpowers skill (version 1.0.0, MIT) that dispatches a code-review sub-agent after tasks complete, major features land, or before merging to main. The reviewer receives organized evaluation context—description, plan or requirements, BASE_SHA, and HEAD_SHA—not the author's session history, so review stays focused on deliverables. Developers also use it when stuck, before refactors, or after complex bug fixes. The workflow uses git rev-parse for SHAs and the Task tool with a code-reviewer template. Core principle: review early and often, especially in subagent-driven development after each task.

  • Dispatches focused review sub-agent using only task context instead of full session history
  • Must-review triggers: after every sub-agent task, after major features, before merging to main
  • Severity-based feedback handling: Critical, Important, Minor with explicit fix-or-record rules
  • 4-step workflow: obtain git SHAs, populate code-reviewer.md template, process feedback, continue
  • Hard-gate rule: never skip review even on simple tasks; never proceed with unresolved Important issues

Requesting Code Review by the numbers

  • 851 all-time installs (skills.sh)
  • +30 installs in the week ending Aug 2, 2026 (Skillselion tracking)
  • Ranked #171 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/jnmetacode/superpowers-zh --skill requesting-code-review

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs851
repo stars7.5k
Last updatedJuly 31, 2026
Repositoryjnmetacode/superpowers-zh

How do you request an independent code review before merging?

Dispatch an independent code-review sub-agent that evaluates completed work against a clean context before merging or moving forward.

Who is it for?

Developers using agent-driven workflows who want fresh-context review after each task, major feature, or before merging to main.

Skip if: Trivial one-line edits where formal sub-agent review overhead exceeds the change risk.

When should I use this skill?

A task completes, an important feature is implemented, the user is stuck and wants a second perspective, or merge to main is imminent.

What you get

A structured code-review report from a sub-agent evaluating the diff between BASE_SHA and HEAD_SHA against stated requirements.

  • code review findings
  • requirements compliance assessment

By the numbers

  • Version 1.0.0 under MIT license

Files

SKILL.mdMarkdownGitHub ↗

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

Related skills

FAQ

When must requesting-code-review be used?

requesting-code-review should run after each subagent-driven task, when important features complete, and before merging to main. Optional uses include getting unstuck, establishing a refactor baseline, or reviewing after complex bug fixes.

What context does the review sub-agent receive?

The review sub-agent gets a curated brief—work description, plan or requirements, BASE_SHA, and HEAD_SHA—from the code-reviewer template. requesting-code-review deliberately excludes the author's session history so review targets deliverables only.

Code Review & Qualitytestingintegrations

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.