Back to Details

kata-review-pull-requests

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Comprehensive PR Review

全面PR审查

Run a comprehensive pull request review using multiple specialized agents, each focusing on a different aspect of code quality.
Review Aspects (optional): "$ARGUMENTS"
使用多个专业Agent执行全面的拉取请求（PR）审查，每个Agent专注于代码质量的不同方面。
审查维度（可选）： "$ARGUMENTS"

Review Workflow:

审查工作流：

  1. Determine Review Scope
    • Check git status to identify changed files
    • Parse arguments to see if user requested specific review aspects
    • Default: Run all applicable reviews
  2. Available Review Aspects:
    • comments - Analyze code comment accuracy and maintainability
    • tests - Review test coverage quality and completeness
    • errors - Check error handling for silent failures
    • types - Analyze type design and invariants (if new types added)
    • code - General code review for project guidelines
    • simplify - Simplify code for clarity and maintainability
    • all - Run all applicable reviews (default)
  3. Identify Changed Files
    • Run 
      git diff --name-only
      to see modified files
    • Check if PR already exists: 
      gh pr view
    • Identify file types and what reviews apply
    Error handling:
    • If 
      git diff
      fails (not a git repo): Report error clearly and stop
    • If 
      gh pr view
      fails with "no PR found": Expected for pre-PR reviews, continue with git diff
    • If 
      gh pr view
      fails with auth error: Note that GitHub CLI authentication is needed
    • If no changed files found: Report "No changes detected" and stop
  4. Determine Applicable Reviews
    Based on changes:
    • Always applicable: kata-code-reviewer (general quality)
    • If test files changed: kata-pr-test-analyzer
    • If comments/docs added: kata-comment-analyzer
    • If error handling changed: kata-failure-finder
    • If types added/modified: kata-type-design-analyzer
    • After passing review: kata-code-simplifier (polish and refine)
  5. Launch Review Agents
    Sequential approach (one at a time):
    • Easier to understand and act on
    • Each report is complete before next
    • Good for interactive review
    Parallel approach (user can request):
    • Launch all agents simultaneously
    • Faster for comprehensive review
    • Results come back together
    Agent failure handling:
    • If agent completes: Include results in aggregation
    • If agent times out: Report "[agent-name] timed out - consider running independently"
    • If agent fails: Report "[agent-name] failed: [error reason]"
    • If one agent fails, STILL proceed with remaining agents
    • Never silently skip a failed agent - always report its status
  6. Aggregate Results
    After agents complete, summarize:
    • Critical Issues (must fix before merge)
    • Important Issues (should fix)
    • Suggestions (nice to have)
    • Positive Observations (what's good)
    Edge cases:
    • If no issues found: Celebrate with "All Checks Passed" summary
    • If agents conflict: Note the disagreement and let user decide
    • If agent output malformed: Note "[agent] output could not be parsed"
    • Always include count of agents completed vs failed
  7. Provide Action Plan
    Organize findings:
    markdown
    # PR Review Summary

## Critical Issues (X found)
- [agent-name]: Issue description [file:line]

## Important Issues (X found)
- [agent-name]: Issue description [file:line]

## Suggestions (X found)
- [agent-name]: Suggestion [file:line]

## Strengths
- What's well-done in this PR

## Recommended Action
1. Fix critical issues first
2. Address important issues
3. Consider suggestions
4. Re-run review after fixes
  1. 确定审查范围
    • 执行
      git status
      命令识别变更文件
    • 解析参数，查看用户是否指定了特定审查维度
    • 默认：运行所有适用的审查
  2. 可用审查维度：
    • comments - 分析代码注释的准确性与可维护性
    • tests - 审查测试覆盖率的质量与完整性
    • errors - 检查错误处理是否存在静默故障
    • types - 分析类型设计与不变量（如果新增了类型）
    • code - 基于项目规范的通用代码审查
    • simplify - 简化代码以提升清晰度与可维护性
    • all - 运行所有适用的审查（默认选项）
  3. 识别变更文件
    • 执行
      git diff --name-only
      查看修改的文件
    • 检查PR是否已存在：
      gh pr view
    • 识别文件类型及适用的审查维度
    错误处理：
    • 若
      git diff
      执行失败（当前目录不是git仓库）：清晰报告错误并终止流程
    • 若
      gh pr view
      执行失败并提示"no PR found"：属于PR创建前的审查场景，继续基于git diff结果执行
    • 若
      gh pr view
      因认证错误失败：提示需要完成GitHub CLI认证
    • 若未发现变更文件：报告"未检测到任何变更"并终止流程
  4. 确定适用的审查
    根据变更内容：
    • 始终适用：kata-code-reviewer（通用质量审查）
    • 若测试文件变更：kata-pr-test-analyzer
    • 若添加了注释/文档：kata-comment-analyzer
    • 若错误处理逻辑变更：kata-failure-finder
    • 若类型新增/修改：kata-type-design-analyzer
    • 审查通过后：kata-code-simplifier（代码优化与精炼）
  5. 启动审查Agent
    串行模式（依次执行）：
    • 结果更易理解与跟进
    • 每个Agent完成审查后再启动下一个
    • 适合交互式审查场景
    并行模式（用户可主动请求）：
    • 同时启动所有Agent
    • 全面审查速度更快
    • 所有结果同时返回
    Agent故障处理：
    • 若Agent执行完成：将结果纳入汇总
    • 若Agent超时：报告"[agent-name] 超时 - 建议单独运行该Agent"
    • 若Agent执行失败：报告"[agent-name] 执行失败：[错误原因]"
    • 即使某个Agent失败，仍继续执行剩余Agent
    • 绝不静默跳过失败的Agent - 必须始终报告其状态
  6. 汇总审查结果
    所有Agent完成后，汇总内容包括：
    • 关键问题（合并前必须修复）
    • 重要问题（建议修复）
    • 优化建议（可选修复）
    • 正面评价（代码亮点）
    边缘场景处理：
    • 若未发现任何问题：显示"所有检查通过"的总结
    • 若Agent结果存在冲突：标注分歧并由用户决定
    • 若Agent输出格式异常：标注"[agent] 输出内容无法解析"
    • 始终统计已完成与失败的Agent数量
  7. 提供改进行动计划
    整理审查结果为以下格式：
    markdown
    # PR审查总结

## 关键问题（共X个）
- [agent-name]: 问题描述 [文件:行号]

## 重要问题（共X个）
- [agent-name]: 问题描述 [文件:行号]

## 优化建议（共X个）
- [agent-name]: 建议内容 [文件:行号]

## 代码亮点
- 本次PR中的优秀实践

## 推荐行动步骤
1. 优先修复关键问题
2. 处理重要问题
3. 考虑采纳优化建议
4. 修复后重新运行审查

Usage Examples:

使用示例：

Full review (default):
/kata-review-pull-requests
Specific aspects:
/kata-review-pull-requests tests errors
全面审查（默认）：
/kata-review-pull-requests
指定审查维度：
/kata-review-pull-requests tests errors

Reviews only test coverage and error handling

仅审查测试覆盖率与错误处理

/kata-review-pull-requests comments
/kata-review-pull-requests comments

Reviews only code comments

仅审查代码注释

/kata-review-pull-requests simplify
/kata-review-pull-requests simplify

Simplifies code after passing review

审查通过后简化代码


**Parallel review:**
/kata-review-pull-requests all parallel

**并行审查：**
/kata-review-pull-requests all parallel

Launches all agents in parallel

并行启动所有Agent

undefined
undefined

Agent Descriptions:

Agent说明：

kata-comment-analyzer:
  • Verifies comment accuracy vs code
  • Identifies comment rot
  • Checks documentation completeness
kata-pr-test-analyzer:
  • Reviews behavioral test coverage
  • Identifies critical gaps
  • Evaluates test quality
kata-failure-finder:
  • Finds silent failures
  • Reviews catch blocks
  • Checks error logging
kata-type-design-analyzer:
  • Analyzes type encapsulation
  • Reviews invariant expression
  • Rates type design quality
kata-code-reviewer:
  • Checks CLAUDE.md compliance
  • Detects bugs and issues
  • Reviews general code quality
kata-code-simplifier:
  • Simplifies complex code
  • Improves clarity and readability
  • Applies project standards
  • Preserves functionality
kata-comment-analyzer:
  • 验证注释与代码的一致性
  • 识别过时注释
  • 检查文档完整性
kata-pr-test-analyzer:
  • 审查行为测试覆盖率
  • 识别关键测试缺口
  • 评估测试质量
kata-failure-finder:
  • 发现静默故障
  • 审查catch块逻辑
  • 检查错误日志实现
kata-type-design-analyzer:
  • 分析类型封装性
  • 审查不变量表达式
  • 评估类型设计质量
kata-code-reviewer:
  • 检查是否符合CLAUDE.md规范
  • 检测潜在bug与问题
  • 审查通用代码质量
kata-code-simplifier:
  • 简化复杂代码逻辑
  • 提升代码清晰度与可读性
  • 遵循项目规范
  • 保留原有功能

Tips:

使用提示：

  • Run early: Before creating PR, not after
  • Focus on changes: Agents analyze git diff by default
  • Address critical first: Fix high-priority issues before lower priority
  • Re-run after fixes: Verify issues are resolved
  • Use specific reviews: Target specific aspects when you know the concern
  • 尽早运行：在创建PR前运行，而非之后
  • 聚焦变更：Agent默认仅分析git diff中的变更内容
  • 优先处理关键问题：先修复高优先级问题，再处理低优先级问题
  • 修复后重新运行：验证问题是否已解决
  • 使用指定维度审查：当明确关注点时，针对性选择审查维度

Workflow Integration:

工作流集成：

Before committing:
1. Write code
2. Run: /kata-review-pull-requests code errors
3. Fix any critical issues
4. Commit
Before creating PR:
1. Stage all changes
2. Run: /kata-review-pull-requests all
3. Address all critical and important issues
4. Run specific reviews again to verify
5. Create PR
After PR feedback:
1. Make requested changes
2. Run targeted reviews based on feedback
3. Verify issues are resolved
4. Push updates
提交代码前：
1. 编写代码
2. 运行：/kata-review-pull-requests code errors
3. 修复所有关键问题
4. 提交代码
创建PR前：
1. 暂存所有变更
2. 运行：/kata-review-pull-requests all
3. 处理所有关键与重要问题
4. 再次运行指定维度审查以验证
5. 创建PR
收到PR反馈后：
1. 根据反馈修改代码
2. 针对反馈内容运行指定维度审查
3. 验证问题是否已解决
4. 推送更新