Back to Details

review-quick

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
<!-- markdownlint-disable-file MD041 -->
STARTER_CHARACTER = ⚡
<!-- markdownlint-disable-file MD041 -->
STARTER_CHARACTER = ⚡

Quick Review

快速审查

Review work-in-progress and recent commits across 8 focus areas in parallel. No arguments. Auto-detects deltas.
并行审查8个重点领域的进行中工作和最近提交。无需参数，自动检测差异。

Step 1: Detect Deltas

步骤1：检测差异

Compute what changed since the project root was last touched. Span committed, staged, unstaged, and untracked work.
bash
PROJECT_ROOT=$(git rev-parse --show-toplevel)
BASELINE=$(git log -1 --format=%H -- "$PROJECT_ROOT")
[ -z "$BASELINE" ] && BASELINE=$(git rev-list --max-parents=0 HEAD)

git log --oneline ${BASELINE}..HEAD
git diff ${BASELINE} --find-renames --stat
git diff ${BASELINE} --find-renames
git status --porcelain
git ls-files --others --exclude-standard
The diff has no 
..HEAD
so it spans the baseline through the working tree, including staged and unstaged edits. 
--find-renames
surfaces renames as 
R<score>
entries with both old and new paths so a pure rename does not collapse into an empty diff. 
git status --porcelain
is the authoritative list of every modified, added, deleted, renamed, copied, and untracked entry; use it to confirm rename detection. 
ls-files --others
surfaces new untracked files. Files matching 
.gitignore
are excluded.
Stop only if all four signals are empty: 
git diff
empty, 
git status --porcelain
empty, 
ls-files --others
empty, and 
git log ${BASELINE}..HEAD
empty. Then report "No deltas to review" and stop.
计算自上次修改项目根目录以来的变更内容，涵盖已提交、已暂存、未暂存和未跟踪的工作内容。
bash
PROJECT_ROOT=$(git rev-parse --show-toplevel)
BASELINE=$(git log -1 --format=%H -- "$PROJECT_ROOT")
[ -z "$BASELINE" ] && BASELINE=$(git rev-list --max-parents=0 HEAD)

git log --oneline ${BASELINE}..HEAD
git diff ${BASELINE} --find-renames --stat
git diff ${BASELINE} --find-renames
git status --porcelain
git ls-files --others --exclude-standard
该diff没有
..HEAD
，因此它涵盖了从基线到工作区的所有内容，包括已暂存和未暂存的编辑。
--find-renames
会将重命名显示为带有新旧路径的
R<score>
条目，这样纯重命名不会变成空diff。
git status --porcelain
是所有已修改、已添加、已删除、已重命名、已复制和未跟踪条目的权威列表，可用于确认重命名检测结果。
ls-files --others
会显示新的未跟踪文件，匹配
.gitignore
的文件会被排除。
仅当四个信号均为空时才停止：
git diff
为空、
git status --porcelain
为空、
ls-files --others
为空，且
git log ${BASELINE}..HEAD
为空。此时报告“无差异可审查”并停止。

Step 2: Read Untracked Files

步骤2：读取未跟踪文件

For each file from 
git ls-files --others --exclude-standard
, read the full file content. Untracked files have no diff representation.
对于
git ls-files --others --exclude-standard
列出的每个文件，读取完整的文件内容。未跟踪文件没有diff表示形式。

Step 3: Dispatch 8 Review Agents in Parallel

步骤3：并行调度8个审查Agent

Dispatch 8 parallel reviews, one per focus area. Use subagents if available, otherwise run sequentially:
AgentSubagent type
Architecture & Design
review-architecture
Correctness & Bugs
review-correctness
Operational Readiness
review-ops
Performance
review-performance
Code Quality
review-quality
Security
review-security
SOLID Principles
review-solid
Testing
review-testing
Each review prompt contains:
  1. The full diff output from Step 1
  2. The contents of any untracked files from Step 2
  3. The instruction: "Review the following changes for your focus area. Return findings as your response."
Do not pack repomix. Each agent has all the context needed in the prompt.
并行调度8个审查任务，每个重点领域一个。如果有子Agent则使用，否则按顺序运行：
Agent类型子Agent类型
Architecture & Design
review-architecture
Correctness & Bugs
review-correctness
Operational Readiness
review-ops
Performance
review-performance
Code Quality
review-quality
Security
review-security
SOLID Principles
review-solid
Testing
review-testing
每个审查提示包含：
  1. 步骤1生成的完整diff输出
  2. 步骤2中所有未跟踪文件的内容
  3. 指令：“针对你的重点领域审查以下变更，返回审查结果作为响应。”
不要打包repomix。每个Agent的提示中都包含所需的全部上下文。

Step 4: Consolidate Findings

步骤4：整合审查结果

After all 8 agents return, produce a single consolidated report:
markdown
undefined
在所有8个Agent返回结果后，生成一份整合后的报告：
markdown
undefined

Quick Review Report

Quick Review Report

Summary

Summary

  • Total findings: <N>
  • High: <count>
  • Medium: <count>
  • Low: <count>
  • Total findings: <N>
  • High: <count>
  • Medium: <count>
  • Low: <count>

Findings by Severity

Findings by Severity

High

High

[All High findings from all 8 agents, ordered by file:line]
[All High findings from all 8 agents, ordered by file:line]

Medium

Medium

[All Medium findings from all 8 agents, ordered by file:line]
[All Medium findings from all 8 agents, ordered by file:line]

Low

Low

[All Low findings from all 8 agents, ordered by file:line]
undefined
[All Low findings from all 8 agents, ordered by file:line]
undefined

When to Use

使用场景

This skill auto-loads when:
  • A bug fix or feature implementation has just been completed
  • Work is about to be committed or a PR is about to be opened
  • A subagent-driven-development task has just passed spec compliance review
It is also slash-invokable for ad-hoc review of current work.
在以下场景下，该Skill会自动加载：
  • 刚完成bug修复或功能实现
  • 即将提交工作或打开PR
  • 子Agent驱动的开发任务刚通过规范合规审查
它也可以通过斜杠调用，用于临时审查当前工作。