review-it

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

CC Review

CC代码审查

Run automated code review as a closeout check before committing or shipping. Works across multiple AI coding agents.
Use when:
  • user asks for code review / review-it / autoreview
  • after non-trivial code edits, before final/commit/ship
  • reviewing a local branch or PR branch after fixes
在提交或发布前,将自动化代码审查作为收尾检查步骤。支持多款AI代码Agent。
适用场景:
  • 用户要求进行代码审查/review-it/autoreview
  • 在完成非琐碎代码编辑后,最终提交/发布前
  • 修复完成后审查本地分支或PR分支

Supported Agents

支持的Agent

AgentReview CommandNotes
Claude Code
/review
Built-in, works on uncommitted changes or diff
Codex
codex review
Pass diff file or let it auto-detect
OpenCode
/review
Same as Claude Code
DeepSeek TUI
/review
or manual diff review
Pass diff content for analysis
Agent审查命令说明
Claude Code
/review
内置功能,可处理未提交变更或差异内容
Codex
codex review
传入差异文件或让其自动检测
OpenCode
/review
与Claude Code相同
DeepSeek TUI
/review
或手动差异审查
传入差异内容进行分析

Contract

审查约定

  • Treat review output as advisory. Never blindly apply it.
  • Verify every finding by reading the real code path and adjacent files.
  • Read dependency docs/source/types when the finding depends on external behavior.
  • Reject unrealistic edge cases, speculative risks, broad rewrites, and fixes that over-complicate the codebase.
  • Prefer small fixes at the right ownership boundary; no refactor unless it clearly improves the bug class.
  • Keep going until review returns no accepted/actionable findings.
  • If a review-triggered fix changes code, rerun focused tests and rerun review.
  • Stop as soon as the review comes back clean with no actionable findings.
  • If rejecting a finding as intentional/not worth fixing, add a brief inline code comment only when it explains a real invariant or ownership decision that future reviewers should know.
  • Do not push just to review. Push only when the user requested push/ship/PR update.
  • 将审查结果视为建议,切勿盲目采纳。
  • 通过阅读实际代码路径及关联文件,验证每一项审查发现。
  • 当审查发现涉及外部行为时,查阅依赖文档/源码/类型定义。
  • 拒绝不切实际的边缘案例、推测性风险、大范围重写以及会过度复杂化代码库的修复方案。
  • 优先在合适的职责边界处进行小修复;除非能明确改善bug类别,否则不进行重构。
  • 持续执行审查,直到没有可接受/可执行的审查发现为止。
  • 若审查触发的修复修改了代码,重新运行针对性测试并再次执行审查。
  • 一旦审查结果无任何可执行发现,立即停止。
  • 若因设计需求/修复性价比低而拒绝某项审查发现,仅当该决定能解释未来审查者应了解的真实约束或职责划分时,添加简短的内联代码注释。
  • 不要仅为了审查而推送代码。仅当用户要求推送/发布/更新PR时才进行推送。

Pick Target

选择审查目标

Claude Code / OpenCode / DeepSeek TUI

Claude Code / OpenCode / DeepSeek TUI

Dirty local work (default —
/review
works on uncommitted changes):
/review
Branch/PR work — review all changes against base:
First generate a diff, then review it:
bash
git diff origin/main...HEAD > /tmp/review-it.diff
Then review the diff file with a focused prompt:
/review the changes in /tmp/review-it.diff against origin/main
If an open PR exists, use its actual base:
bash
base=$(gh pr view --json baseRefName --jq .baseRefName)
git diff "origin/$base"...HEAD > /tmp/review-it.diff
本地未提交工作(默认 —
/review
可处理未提交变更):
/review
分支/PR工作 — 审查相对于基准分支的所有变更:
先生成差异文件,再进行审查:
bash
git diff origin/main...HEAD > /tmp/review-it.diff
然后使用针对性提示审查差异文件:
/review the changes in /tmp/review-it.diff against origin/main
若存在已打开的PR,使用其实际基准分支:
bash
base=$(gh pr view --json baseRefName --jq .baseRefName)
git diff "origin/$base"...HEAD > /tmp/review-it.diff

Codex

Codex

bash
undefined
bash
undefined

Review uncommitted changes

审查未提交变更

codex review
codex review

Review branch diff

审查分支差异

git diff origin/main...HEAD > /tmp/review-it.diff codex review /tmp/review-it.diff
undefined
git diff origin/main...HEAD > /tmp/review-it.diff codex review /tmp/review-it.diff
undefined

Parallel Closeout

并行收尾操作

Format first if formatting can change line locations. Then it's OK to run tests and review in parallel:
bash
scripts/review-it --parallel-tests "<focused test command>"
Tradeoff: tests may force code changes that stale the review. If tests or review lead to code edits, rerun the affected tests and rerun review until no accepted/actionable findings remain.
若代码格式化会改变行位置,请先执行格式化。之后可并行运行测试与审查:
bash
scripts/review-it --parallel-tests "<focused test command>"
权衡:测试可能会迫使代码变更,导致审查结果失效。若测试或审查引发代码编辑,重新运行受影响的测试并再次执行审查,直到没有可接受/可执行的发现为止。

Uncommitted vs Branch Review

未提交变更与分支审查对比

Choose the right mode:
  • Uncommitted changes (staged/unstaged): use
    /review
    directly (or
    codex review
    )
  • Committed, not pushed: use
    git diff origin/main...HEAD
    + review
  • Pushed/PR: same as committed, against the PR base
  • Clean working tree: skip review if there's truly nothing to review
选择合适的模式:
  • 未提交变更(已暂存/未暂存):直接使用
    /review
    (或
    codex review
  • 已提交但未推送:使用
    git diff origin/main...HEAD
    + 审查
  • 已推送/PR:与已提交未推送情况相同,对比PR基准分支
  • 干净工作区:若确实无内容可审查,跳过审查

Helper

辅助脚本

Bundled helper script for parallel test + review orchestration:
bash
~/.claude/skills/review-it/scripts/review-it --help
The helper:
  • Detects whether to use uncommitted review or branch diff review
  • For branch mode: generates diff against
    origin/main
    (or PR base), then triggers review
  • Supports
    --parallel-tests
    for concurrent test + review execution
  • Supports
    --dry-run
    for checking what command would be used
  • Prints
    review-it clean: no accepted/actionable findings reported
    when review is clean
用于并行测试+审查编排的内置辅助脚本:
bash
~/.claude/skills/review-it/scripts/review-it --help
该辅助脚本:
  • 自动检测应使用未提交变更审查还是分支差异审查
  • 分支模式下:生成与
    origin/main
    (或PR基准分支)的差异文件,然后触发审查
  • 支持
    --parallel-tests
    参数以并发执行测试与审查
  • 支持
    --dry-run
    参数以查看将执行的命令
  • 当审查无问题时,输出
    review-it clean: no accepted/actionable findings reported

Final Report

最终报告

Include:
  • review target (uncommitted / branch / PR base)
  • tests/proof run
  • findings accepted/rejected, briefly why
  • the clean review result, or why a remaining finding was consciously rejected
Do not run another review solely to improve the final report wording. If review exited clean with no actionable findings, report that as clean.
需包含:
  • 审查目标(未提交变更/分支/PR基准分支)
  • 运行的测试/验证依据
  • 接受/拒绝的审查发现及简要原因
  • 审查通过结果,或为何有意识地保留某项发现的原因
不要仅为优化最终报告措辞而再次运行审查。若审查无任何可执行发现且顺利结束,直接报告审查通过即可。