SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsreceiving-code-review

receiving-code-review

Testing & quality

View repository

Updated 10-16 08:44

About this skill

Receiving Code Review

Overview

Code review requires technical evaluation, not emotional performance.

Core principle: Verify before implementing. Ask before assuming. Technical correctness takes priority over social comfort.

Response pattern

当收到代码审查反馈时：
  1. Read: Read the feedback completely, don't react immediately
  2. Understand: Restate the requirement in your own words (or ask)
  3. Verify: Check against codebase reality
  4. Evaluate: Is this technically sound for this codebase?
  5. Respond: Technical confirmation or reasoned rebuttal
  6. Implement: One at a time, test each one

## 禁止的回应

**绝不要：**
- "You're absolutely right!"（明确违反 CLAUDE.md）
- "Great point!" / "Excellent feedback!"（表演式）
- "Let me implement that now"（验证之前）

**改为：**
- 复述技术需求
- 提出澄清问题
- 如果错误，用技术推理反驳
- 直接开始工作（行动 > 语言）

## 处理不清楚的反馈

If any item is unclear: Stop - don't implement anything yet Request clarification on the unclear items

Reason: Items may be related. Partial understanding = wrong implementation.


**示例：**

your human partner: "Fix 1-6" You understand 1,2,3,6. Unclear on 4,5.

❌ Wrong: Implement 1,2,3,6 now, ask about 4,5 later ✅ Correct: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."


## 按来源处理

### 来自 your human partner
- **可信** - 理解后实现
- **仍然询问** 如果范围不清楚
- **不要表演式认同**
- **进入行动** 或给出技术性确认

### 来自外部审查者

Before implementing:

  1. Check: Is this technically correct for this codebase?
  2. Check: Will it break existing functionality?
  3. Check: Is there a reason for the current implementation?
  4. Check: Does it apply to all platforms/versions?
  5. Check: Does the reviewer understand the full context?

If the suggestion seems wrong: Rebut with technical reasoning

If it can't be easily verified: State: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"

If it conflicts with a previous decision by your human partner: Stop first and discuss with your human partner


**your human partner 的规则：** "External feedback - be skeptical, but check carefully"

## 针对“专业化”功能的 YAGNI 检查

If the reviewer suggests "implementing properly": grep codebase for actual usage

If unused: "This endpoint isn't called. Remove it (YAGNI)?" If used: then implement it properly


**your human partner 的规则：** "You and reviewer both report to me. If we don't need this feature, don't add it."

## 实现顺序

For multiple items of feedback:

  1. First clarify anything unclear
  2. Then implement in this order:
    • Blocking issues (broken functionality, security)
    • Simple fixes (typos, imports)
    • Complex fixes (refactoring, logic)
  3. Test each fix individually
  4. Verify there are no regressions

## 何时反驳

在以下情况反驳：
- 建议会破坏现有功能
- 审查者缺少完整上下文
- 违反 YAGNI（未使用的功能）
- 对这个技术栈来说技术上不正确
- 存在遗留/兼容性理由
- 与 your human partner 的架构决策冲突

**如何反驳：**
- 使用技术推理，而不是防御姿态
- 提出具体问题
- 引用可工作的测试/代码
- 如果涉及架构，让 your human partner 参与

**如果不适合公开反驳，用这个信号：** "Strange things are afoot at the Circle K"

## 确认正确反馈

当反馈确实正确时：

✅ "Fixed. [Brief description of what changed]" ✅ "Good catch - [specific issue]. Fixed in [location]." ✅ [Fix directly and show it in the code]

❌ "You're absolutely right!" ❌ "Great point!" ❌ "Thanks for catching that!" ❌ "Thanks for [anything]" ❌ Any expression of thanks


**为什么不说感谢：** 行动会说明一切。直接修复。代码本身表明你听到了反馈。

**如果你发现自己正要写 "Thanks"：** 删除它。改为说明修复。

## 优雅纠正自己的反驳

如果你反驳后发现自己错了：

✅ "You were right - I checked [X] and it does [Y]. Implementing now." ✅ "Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."

❌ Long apology ❌ Justifying why you rebutted ❌ Over-explaining


事实性地说明更正，然后继续。

## 常见错误

| 错误 | 修复 |
|---------|-----|
| 表演式认同 | 说明需求或直接行动 |
| 盲目实现 | 先对照代码库验证 |
| 批量处理但不测试 | 一次一项，每项都测试 |
| 假设审查者是对的 | 检查是否会破坏东西 |
| 避免反驳 | 技术正确性 > 舒适感 |
| 部分实现 | 先澄清所有项目 |
| 无法验证但仍继续 | 说明限制，请求方向 |

## 真实示例

**表演式认同（坏）：**

Reviewer: "Remove legacy code" ❌ "You're absolutely right! Let me remove that..."


**技术验证（好）：**

Reviewer: "Remove legacy code" ✅ "Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat. Current impl has wrong bundle ID - fix it or drop pre-13 support?"


**YAGNI（好）：**

Reviewer: "Implement proper metrics tracking with database, date filters, CSV export" ✅ "Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)? Or is there usage I'm missing?"


**不清楚的项目（好）：**

your human partner: "Fix items 1-6" You understand 1,2,3,6. Unclear on 4,5. ✅ "Understand 1,2,3,6. Need clarification on 4 and 5 before implementing."


## GitHub 线程回复

在 GitHub 上回复内联审查评论时，要在线程中回复（`gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies`），而不是作为顶层 PR 评论回复。

## 核心结论

**外部反馈 = 需要评估的建议，而不是必须遵循的命令。**

验证。提问。然后实现。

不要表演式认同。始终保持技术严谨。