代码审查最佳实践指南：技术严谨性、验证优先与子代理审查流程

code-review by mrgoonie/claudekit-skills

304 周安装量

1,900 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/mrgoonie/claudekit-skills --skill code-review

质量管理开发代码规范

🇨🇳中文介绍

代码审查

指导正确的代码审查实践，强调技术严谨性、基于证据的主张，以及验证优先于形式化回应。

概述

代码审查需要三种不同的实践：

接收反馈 - 技术评估优先于形式上的同意
请求审查 - 通过 code-reviewer 子代理进行系统性审查
验证关卡 - 在做出任何完成声明之前提供证据

每种实践都有特定的触发条件和详细协议，记录在参考文件中。

核心原则

技术正确性高于社交舒适度。 在实施前验证。在假设前询问。在声明前提供证据。

何时使用此技能

接收反馈

在以下情况触发：

从任何来源收到代码审查意见时
反馈看起来不明确或在技术上存疑时
需要优先处理多个审查项时
外部审查者缺乏完整上下文时
建议与现有决策冲突时

参考： references/code-review-reception.md

请求审查

在以下情况触发：

在子代理驱动开发中完成每个任务后
完成主要功能或重构后
合并到主分支之前
遇到瓶颈需要新视角时
修复复杂错误后

参考： references/requesting-code-review.md

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

762,600 周安装

Vercel React 最佳实践指南 | 58条Next.js性能优化规则与代码重构

258,600 周安装

Vercel Web界面规范检查工具 - 自动检测代码是否符合Web设计指南

208,300 周安装

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

138,300 周安装

在以下情况触发：

即将声明测试通过、构建成功或工作完成时
提交、推送或创建 PR 之前
转向下一个任务时
任何暗示成功/完成的陈述时
表达对工作满意时

参考： references/verification-before-completion.md

SITUATION?
│
├─ Received feedback
│  ├─ Unclear items? → STOP, ask for clarification first
│  ├─ From human partner? → Understand, then implement
│  └─ From external reviewer? → Verify technically before implementing
│
├─ Completed work
│  ├─ Major feature/task? → Request code-reviewer subagent review
│  └─ Before merge? → Request code-reviewer subagent review
│
└─ About to claim status
   ├─ Have fresh verification? → State claim WITH evidence
   └─ No fresh verification? → RUN verification command first

阅读 → 理解 → 验证 → 评估 → 回应 → 实施

❌ 不要形式化同意："你说得完全对！"、"好观点！"、"谢谢[任何内容]"
❌ 不要在验证前实施
✅ 重述要求、提出问题、用技术推理反驳，或者直接开始工作
✅ 如果不明确：立即停止，首先询问所有不明确的事项
✅ YAGNI 检查：在实施建议的"正确"功能前，先用 grep 检查使用情况

人类伙伴： 可信赖 - 在理解后实施，无需形式化同意
外部审查者： 验证技术正确性，检查是否会造成破坏，如果错误则进行反驳

完整协议： references/code-review-reception.md

在子代理驱动开发中完成每个任务后
完成主要功能后
合并到主分支之前

获取 git SHA：BASE_SHA=$(git rev-parse HEAD~1) 和 HEAD_SHA=$(git rev-parse HEAD)
通过 Task 工具分派 code-reviewer 子代理，附带：WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, DESCRIPTION
处理反馈：立即修复 Critical 级别，在继续前修复 Important 级别，记录 Minor 级别稍后处理

完整协议： references/requesting-code-review.md

没有最新的验证证据，不得做出完成声明

识别命令 → 运行完整命令 → 读取输出 → 验证确认声明 → 然后声明

跳过任何一步 = 撒谎，而非验证

测试通过：测试输出显示 0 个失败
构建成功：构建命令退出码为 0
错误已修复：原始症状测试通过
需求满足：逐行检查清单已验证

危险信号 - 立即停止

使用"应该"/"可能"/"似乎"，在验证前表达满意，未经验证就提交，信任代理报告，任何暗示成功但未运行验证的措辞

完整协议： references/verification-before-completion.md

子代理驱动： 每个任务后审查，在转向下一个任务前验证
拉取请求： 验证测试通过，在合并前请求 code-reviewer 审查
通用： 在任何状态声明前应用验证关卡，对无效反馈进行反驳

技术严谨性高于社交表现 - 不要形式化同意
系统性审查流程 - 使用 code-reviewer 子代理
证据先于声明 - 始终使用验证关卡

验证。质疑。然后实施。证据。然后声明。

🇺🇸English

Code Review

Guide proper code review practices emphasizing technical rigor, evidence-based claims, and verification over performative responses.

Overview

Code review requires three distinct practices:

Receiving feedback - Technical evaluation over performative agreement
Requesting reviews - Systematic review via code-reviewer subagent
Verification gates - Evidence before any completion claims

Each practice has specific triggers and protocols detailed in reference files.

Core Principle

Technical correctness over social comfort. Verify before implementing. Ask before assuming. Evidence before claims.

When to Use This Skill

Receiving Feedback

Trigger when:

Receiving code review comments from any source
Feedback seems unclear or technically questionable
Multiple review items need prioritization
External reviewer lacks full context
Suggestion conflicts with existing decisions

Reference: references/code-review-reception.md

Requesting Review

Trigger when:

Completing tasks in subagent-driven development (after EACH task)
Finishing major features or refactors
Before merging to main branch
Stuck and need fresh perspective
After fixing complex bugs

Reference: references/requesting-code-review.md

Verification Gates

Trigger when:

About to claim tests pass, build succeeds, or work is complete
Before committing, pushing, or creating PRs
Moving to next task
Any statement suggesting success/completion
Expressing satisfaction with work

Reference: references/verification-before-completion.md

Quick Decision Tree

SITUATION?
│
├─ Received feedback
│  ├─ Unclear items? → STOP, ask for clarification first
│  ├─ From human partner? → Understand, then implement
│  └─ From external reviewer? → Verify technically before implementing
│
├─ Completed work
│  ├─ Major feature/task? → Request code-reviewer subagent review
│  └─ Before merge? → Request code-reviewer subagent review
│
└─ About to claim status
   ├─ Have fresh verification? → State claim WITH evidence
   └─ No fresh verification? → RUN verification command first

Receiving Feedback Protocol

Response Pattern

READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT

Key Rules

❌ No performative agreement: "You're absolutely right!", "Great point!", "Thanks for [anything]"
❌ No implementation before verification
✅ Restate requirement, ask questions, push back with technical reasoning, or just start working
✅ If unclear: STOP and ask for clarification on ALL unclear items first
✅ YAGNI check: grep for usage before implementing suggested "proper" features

Source Handling

Human partner: Trusted - implement after understanding, no performative agreement
External reviewers: Verify technically correct, check for breakage, push back if wrong

Full protocol: references/code-review-reception.md

Requesting Review Protocol

When to Request

After each task in subagent-driven development
After major feature completion
Before merge to main

Process

Get git SHAs: BASE_SHA=$(git rev-parse HEAD~1) and HEAD_SHA=$(git rev-parse HEAD)
Dispatch code-reviewer subagent via Task tool with: WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, DESCRIPTION
Act on feedback: Fix Critical immediately, Important before proceeding, note Minor for later

Full protocol: references/requesting-code-review.md

Verification Gates Protocol

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

Gate Function

IDENTIFY command → RUN full command → READ output → VERIFY confirms claim → THEN claim

Skip any step = lying, not verifying

Requirements

Tests pass: Test output shows 0 failures
Build succeeds: Build command exit 0
Bug fixed: Test original symptom passes
Requirements met: Line-by-line checklist verified

Red Flags - STOP

Using "should"/"probably"/"seems to", expressing satisfaction before verification, committing without verification, trusting agent reports, ANY wording implying success without running verification

Full protocol: references/verification-before-completion.md

Integration with Workflows

Subagent-Driven: Review after EACH task, verify before moving to next
Pull Requests: Verify tests pass, request code-reviewer review before merge
General: Apply verification gates before any status claims, push back on invalid feedback

Bottom Line

Technical rigor over social performance - No performative agreement
Systematic review processes - Use code-reviewer subagent
Evidence before claims - Verification gates always

Verify. Question. Then implement. Evidence. Then claim.

Weekly Installs

304

Repository

mrgoonie/claude…t-skills

GitHub Stars

1.9K

First Seen

Jan 22, 2026

Security Audits

Gen Agent Trust HubFail SocketPass SnykPass

Installed on

opencode256

gemini-cli240

claude-code238

codex233

cursor217

github-copilot205

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

105,000 周安装

代码审查最佳实践指南：技术严谨性、验证优先与子代理审查流程

🇨🇳中文介绍

代码审查

概述

核心原则

何时使用此技能

接收反馈

请求审查

相关 Skills

验证关卡

快速决策树

接收反馈协议

响应模式

关键规则

来源处理

请求审查协议

何时请求

流程

验证关卡协议

铁律

关卡功能

要求

危险信号 - 立即停止

与工作流集成

底线

🇺🇸English

Code Review

Overview

Core Principle

When to Use This Skill

Receiving Feedback

Requesting Review

Verification Gates

Quick Decision Tree

Receiving Feedback Protocol

Response Pattern

Key Rules

Source Handling

Requesting Review Protocol

When to Request

Process

Verification Gates Protocol

The Iron Law

Gate Function

Requirements

Red Flags - STOP

Integration with Workflows

Bottom Line

最新 Skills