requesting-code-review
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseRequesting Code Review
发起代码评审
Dispatch superpowers:code-reviewer subagent to catch issues before they cascade.
Core principle: Review early, review often.
调用superpowers:code-reviewer子代理在问题扩大前发现它们。
核心原则: 尽早评审,经常评审。
When to Request Review
何时发起评审
Mandatory:
- After each task in subagent-driven development
- After completing major feature
- Before merge to main
Optional but valuable:
- When stuck (fresh perspective)
- Before refactoring (baseline check)
- After fixing complex bug
强制场景:
- 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main分支前
可选但有价值的场景:
- 遇到瓶颈时(获取新视角)
- 重构前(基线检查)
- 修复复杂bug后
How to Request
如何发起
1. Get git SHAs:
bash
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)2. Dispatch code-reviewer subagent:
Use Task tool with superpowers:code-reviewer type, fill template at
code-reviewer.mdPlaceholders:
- - What you just built
{WHAT_WAS_IMPLEMENTED} - - What it should do
{PLAN_OR_REQUIREMENTS} - - Starting commit
{BASE_SHA} - - Ending commit
{HEAD_SHA} - - Brief summary
{DESCRIPTION}
3. Act on feedback:
- Fix Critical issues immediately
- Fix Important issues before proceeding
- Note Minor issues for later
- Push back if reviewer is wrong (with reasoning)
1. 获取git哈希值:
bash
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)2. 调用code-reviewer子代理:
使用Task工具,选择superpowers:code-reviewer类型,填写中的模板。
code-reviewer.md占位符:
- - 你刚实现的功能
{WHAT_WAS_IMPLEMENTED} - - 功能预期目标
{PLAN_OR_REQUIREMENTS} - - 起始提交哈希
{BASE_SHA} - - 结束提交哈希
{HEAD_SHA} - - 简要说明
{DESCRIPTION}
3. 根据反馈行动:
- 立即修复严重(Critical)问题
- 推进前修复重要(Important)问题
- 记录次要(Minor)问题留待后续处理
- 如果评审者有误,可提出异议(需附上理由)
Example
示例
[Just completed Task 2: Add verification function]
You: Let me request code review before proceeding.
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[Dispatch superpowers:code-reviewer subagent]
WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
[Subagent returns]:
Strengths: Clean architecture, real tests
Issues:
Important: Missing progress indicators
Minor: Magic number (100) for reporting interval
Assessment: Ready to proceed
You: [Fix progress indicators]
[Continue to Task 3][刚完成任务2:添加验证功能]
你:在推进前我要发起代码评审。
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[调用superpowers:code-reviewer子代理]
WHAT_WAS_IMPLEMENTED: 会话索引的验证与修复功能
PLAN_OR_REQUIREMENTS: 来自docs/plans/deployment-plan.md的任务2
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: 新增verifyIndex()和repairIndex()函数,支持4种问题类型
[子代理返回结果]:
优势:架构清晰,包含真实测试
问题:
重要:缺少进度指示器
次要:报告间隔使用了魔法数字(100)
评估:可继续推进
你:[修复进度指示器]
[继续执行任务3]Integration with Workflows
与工作流集成
Subagent-Driven Development:
- Review after EACH task
- Catch issues before they compound
- Fix before moving to next task
Executing Plans:
- Review after each batch (3 tasks)
- Get feedback, apply, continue
Ad-Hoc Development:
- Review before merge
- Review when stuck
子代理驱动开发:
- 完成每个任务后进行评审
- 在问题复杂化前发现它们
- 推进到下一个任务前修复问题
执行计划:
- 每完成一批(3个任务)后进行评审
- 获取反馈,应用后继续
临时开发:
- 合并前进行评审
- 遇到瓶颈时进行评审
Red Flags
注意事项
Never:
- Skip review because "it's simple"
- Ignore Critical issues
- Proceed with unfixed Important issues
- Argue with valid technical feedback
If reviewer wrong:
- Push back with technical reasoning
- Show code/tests that prove it works
- Request clarification
See template at: requesting-code-review/code-reviewer.md
绝对不要:
- 因为“功能简单”而跳过评审
- 忽略严重(Critical)问题
- 带着未修复的重要(Important)问题推进
- 对合理的技术反馈进行争执
如果评审者有误:
- 附上技术理由提出异议
- 展示可证明功能正常的代码/测试
- 请求澄清
查看模板:requesting-code-review/code-reviewer.md