Back to Details

agent-reviews

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
Automatically review, fix, and respond to findings from PR review bots on the current PR. Uses a deterministic two-phase workflow: first fix all existing issues, then poll once for new ones.
Path note: All 
scripts/agent-reviews.js
references below are relative to this skill's directory (next to this SKILL.md file). Run them with 
node
.
自动审查、修复并回复当前PR中PR审查机器人发现的问题。采用确定性的两阶段工作流：首先修复所有现有问题，然后轮询检查新问题。
路径说明： 以下所有对
scripts/agent-reviews.js
的引用均相对于本skill的目录（与SKILL.md文件同级）。使用
node
运行这些脚本。

Phase 1: FETCH & FIX (synchronous)

阶段1：获取并修复（同步）

Step 1: Identify Current PR

步骤1：确定当前PR

bash
gh pr view --json number,url,headRefName
If no PR exists, notify the user and exit.
bash
gh pr view --json number,url,headRefName
如果不存在PR，通知用户并退出。

Step 2: Fetch All Bot Comments (Expanded)

步骤2：获取所有机器人评论（展开详情）

Run 
scripts/agent-reviews.js --bots-only --unanswered --expanded
This shows only unanswered bot comments with full detail: complete comment body (no truncation), diff hunk (code context), and all replies. Each comment shows its ID in brackets (e.g., 
[12345678]
).
If zero comments are returned, print "No unanswered bot comments found" and skip to Phase 2.
运行
scripts/agent-reviews.js --bots-only --unanswered --expanded
该命令仅显示未回复的机器人评论的完整详情：完整评论内容（无截断）、代码差异块（代码上下文）以及所有回复。每条评论的ID会显示在方括号中（例如
[12345678]
）。
如果未返回任何评论，打印“未找到未回复的机器人评论”并跳至阶段2。

Step 3: Process Each Unanswered Comment

步骤3：处理每条未回复的评论

For each comment from the expanded output:
针对展开输出中的每条评论：

A. Evaluate the Finding

A. 评估问题

Read the referenced code and determine:
  1. TRUE POSITIVE - A real bug that needs fixing
  2. FALSE POSITIVE - Not actually a bug (intentional behavior, bot misunderstanding)
  3. UNCERTAIN - Not sure; ask the user
Likely TRUE POSITIVE:
  • Code obviously violates stated behavior
  • Missing null checks on potentially undefined values
  • Type mismatches or incorrect function signatures
  • Logic errors in conditionals
  • Missing error handling for documented failure cases
Likely FALSE POSITIVE:
  • Bot doesn't understand the framework/library patterns
  • Code is intentionally structured that way (with comments explaining why)
  • Bot is flagging style preferences, not bugs
  • The "bug" is actually a feature or intentional behavior
  • Bot misread the code flow
When UNCERTAIN — use 
AskUserQuestion
:
  • The fix would require architectural changes
  • You're genuinely unsure if the behavior is intentional
  • The "bug" relates to business logic you don't fully understand
  • Multiple valid interpretations exist
  • The fix could have unintended side effects
查看引用的代码并判断：
  1. 真实问题 - 需要修复的实际bug
  2. 误报 - 并非实际bug（有意的行为、机器人误解）
  3. 不确定 - 无法确定；询问用户
可能为真实问题的情况：
  • 代码明显违反既定行为规范
  • 对可能未定义的值缺少空值检查
  • 类型不匹配或函数签名错误
  • 条件语句中的逻辑错误
  • 针对文档记录的失败场景缺少错误处理
可能为误报的情况：
  • 机器人不理解框架/库的模式
  • 代码是有意按该结构编写的（并有注释说明原因）
  • 机器人标记的是风格偏好，而非bug
  • 所谓的“bug”实际上是一个功能或有意的行为
  • 机器人误读了代码流程
当不确定时 — 使用
AskUserQuestion
：
  • 修复需要进行架构变更
  • 你确实无法确定该行为是否是有意的
  • 该“bug”与你不完全理解的业务逻辑相关
  • 存在多种合理的解释
  • 修复可能会产生意外的副作用

B. Act on Evaluation

B. 根据评估结果执行操作

If TRUE POSITIVE: Fix the code. Track the comment ID and a brief description of the fix.
If FALSE POSITIVE: Do NOT change the code. Track the comment ID and the reason it's not a real bug.
If UNCERTAIN: Use 
AskUserQuestion
. If the user says skip, track it as skipped.
Do NOT reply to comments yet. Replies happen after the commit (Step 5).
如果是真实问题： 修复代码。记录评论ID和修复的简要描述。
如果是误报： 不要修改代码。记录评论ID和不是真实bug的原因。
如果是不确定： 使用
AskUserQuestion
。如果用户说跳过，将其标记为已跳过。
暂时不要回复评论。回复操作在提交（步骤5）后进行。

Step 4: Commit and Push

步骤4：提交并推送

After evaluating and fixing ALL unanswered comments:
  1. Run your project's lint and type-check
  2. Stage, commit, and push:
    bash
    git add -A
git commit -m "fix: address PR review bot findings

{List of bugs fixed, grouped by bot}"
git push
  3. Capture the commit hash from the output.
在评估并修复所有未回复的评论后：
  1. 运行项目的代码检查和类型校验
  2. 暂存、提交并推送：
    bash
    git add -A
git commit -m "fix: address PR review bot findings

{List of bugs fixed, grouped by bot}"
git push
  3. 从输出中获取提交哈希值。

Step 5: Reply to All Comments

步骤5：回复所有评论

Now that the commit hash exists, reply to every processed comment:
For each TRUE POSITIVE:
Run 
scripts/agent-reviews.js --reply <comment_id> "Fixed in {hash}. {Brief description of the fix}"
For each FALSE POSITIVE:
Run 
scripts/agent-reviews.js --reply <comment_id> "Won't fix: {reason}. {Explanation of why this is intentional or not applicable}"
For each SKIPPED:
Run 
scripts/agent-reviews.js --reply <comment_id> "Skipped per user request"
DO NOT start Phase 2 until all replies are posted.
现在已有提交哈希值，回复每条已处理的评论：
针对每个真实问题：
运行
scripts/agent-reviews.js --reply <comment_id> "Fixed in {hash}. {Brief description of the fix}"
针对每个误报：
运行
scripts/agent-reviews.js --reply <comment_id> "Won't fix: {reason}. {Explanation of why this is intentional or not applicable}"
针对每个已跳过的问题：
运行
scripts/agent-reviews.js --reply <comment_id> "Skipped per user request"
在所有回复发布完成前，不要开始阶段2。

Phase 2: POLL FOR NEW COMMENTS (loop until quiet)

阶段2：轮询新评论（循环直至无新评论）

The watcher exits immediately when new comments are found (after a 5s grace period to catch batch posts). This means you run it in a loop: start watcher, process any comments it returns, restart watcher, repeat until the watcher times out with no new comments.
当发现新评论时（在5秒宽限期后捕获批量发布的评论），监控器会立即退出。这意味着你需要循环运行它：启动监控器，处理它返回的任何评论，重启监控器，重复此过程直到监控器超时且未发现新评论。

Step 6: Start Watcher Loop

步骤6：启动监控器循环

Repeat the following until the watcher exits with no new comments:
6a. Launch the watcher in the background:
Run 
scripts/agent-reviews.js --watch --bots-only
as a background task.
6b. Use 
TaskOutput
to wait for the watcher to complete (blocks up to 12 minutes).
6c. Check the output:
  • If new comments were found (output contains 
    EXITING WITH NEW COMMENTS
    ):
    1. Use 
      --detail <id>
      to read each new comment's full detail
    2. Process them exactly as in Phase 1, Steps 3-5 (evaluate, fix, commit, push, reply)
    3. Go back to Step 6a to restart the watcher
  • If no new comments (output contains 
    WATCH COMPLETE
    ): Stop looping and move to the Summary Report.
重复以下步骤，直到监控器退出且未发现新评论：
6a. 在后台启动监控器：
将
scripts/agent-reviews.js --watch --bots-only
作为后台任务运行。
6b. 使用
TaskOutput
等待监控器完成（最多阻塞12分钟）。
6c. 检查输出：
  • 如果发现新评论（输出包含
    EXITING WITH NEW COMMENTS
    ）：
    1. 使用
      --detail <id>
      查看每条新评论的完整详情
    2. 完全按照阶段1的步骤3-5处理它们（评估、修复、提交、推送、回复）
    3. 回到步骤6a重启监控器
  • 如果未发现新评论（输出包含
    WATCH COMPLETE
    ）： 停止循环并生成总结报告。

Summary Report

总结报告

After both phases complete, provide a summary:
undefined
在两个阶段完成后，提供总结：
undefined

PR Review Bot Resolution Summary

PR审查机器人问题处理总结

Results

结果

  • Fixed: X bugs
  • Already fixed: X bugs
  • Won't fix (false positives): X
  • Skipped per user: X
  • 已修复：X个bug
  • 已自动修复：X个bug
  • 不修复（误报）：X个
  • 按用户要求跳过：X个

By Bot

按机器人分类

cursor[bot]

cursor[bot]

  • BUG-001: {description} - Fixed in {commit}
  • BUG-002: {description} - Won't fix: {reason}
  • BUG-001: {description} - Fixed in {commit}
  • BUG-002: {description} - Won't fix: {reason}

Copilot

Copilot

  • {description} - Fixed in {commit}
  • {description} - Fixed in {commit}

Status

状态

✅ All findings addressed. Watch completed.
undefined
✅ 所有问题已处理。监控完成。
undefined

Important Notes

重要说明

Response Policy

回复策略

  • Every finding gets a response - No silent ignores
  • Responses help train bots and document decisions
  • "Won't fix" responses prevent the same false positive from being re-raised
  • 每个问题都要回复 - 不要默默忽略
  • 回复有助于训练机器人并记录决策
  • “不修复”的回复可以防止相同的误报被再次提出

User Interaction

用户交互

  • Use 
    AskUserQuestion
    when uncertain about a finding
  • Don't guess on architectural or business logic questions
  • It's better to ask than to make a wrong fix or wrong dismissal
  • 当对问题不确定时使用
    AskUserQuestion
  • 不要猜测架构或业务逻辑相关的问题
  • 与其做出错误的修复或错误的驳回，不如询问用户

Best Practices

最佳实践

  • Verify findings before fixing - bots have false positives
  • Keep fixes minimal and focused - don't refactor unrelated code
  • Ensure type-check and lint pass before committing
  • Group related fixes into a single commit
  • Copilot 
    suggestion
    blocks often contain ready-to-use fixes
  • 在修复前验证问题 - 机器人会产生误报
  • 保持修复最小化且聚焦 - 不要重构无关代码
  • 在提交前确保类型校验和代码检查通过
  • 将相关修复合并到一个提交中
  • Copilot的
    suggestion
    块通常包含可直接使用的修复方案