Skip to main content
Category ranking· 品类排行

The best AI skills for code review做代码评审最好用的

Catch risky changes before they land: diff review, style and safety checks.合并之前帮你把关:找出改动里的风险、坏味道和漏掉的测试。

Task shortcuts按用途继续找

Open the matching picks in the full catalog.这些入口会带你去完整目录里看对应用途。

Editor's picks编辑精选榜单

2026-06-09 last re-ranked · 上次重排
#1Gold · 金

GStack Review

Editor's Choice· 编辑首选
by Garry Tan✓ verified·updated 3mo ago

Find the risky changes before the branch lands.

分支合并前,先把真正危险的改动挑出来。

A pre-landing review skill from the gstack toolkit that inspects diffs for trust boundary mistakes, unsafe SQL, conditional side effects, and missing tests.

来自 gstack 的合并前评审技能,重点检查信任边界、SQL 安全风险、隐藏的条件分支副作用与缺失测试。

CodexClaude CodeGit repositoriesLow risk · 低风险$codex /review
4.9
rating · 评分
123k
stars · 星标
View看详情 →
#2Silver · 银

Git Shiproom

Runner-up· 次选
by Garry Stack✓ verified·updated 3mo ago

Pre-flight every branch before you ask for review.

请求评审前,先给分支做一次发布前检查。

A release-oriented Git workflow skill that stages checks, summarizes risk, and prepares clean branch handoff notes.

面向发布的 Git 工作流技能,会串起检查项、总结风险,并整理清晰的分支交接说明。

CodexClaude CodeCursorLow risk · 低风险$codex /shiproom
4.9
rating · 评分
13k
stars · 星标
View看详情 →
#3Bronze · 铜

Review Radar

Pair with #1· 推荐配套
by Garry Stack✓ verified·updated 3mo ago

Find the bugs, regressions, and missing tests first.

先找 bug、回归和缺失测试。

A code review skill tuned to identify breakages and behavioral regressions instead of generating generic summaries.

面向代码评审的技能,重点识别破坏性改动和行为回归,而不是产出泛泛而谈的摘要。

CodexGitHub PR reviewLow risk · 低风险$codex /review-radar
4.8
rating · 评分
11k
stars · 星标
View看详情 →
#4

doubt driven development

by addyosmani·updated 2mo ago

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matter…

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confiden…

Claude CodeMedium risk · 中风险$
rating · 评分
38k
stars · 星标
View看详情 →
#5

ship gate

by alirezarezvani·updated 2mo ago

Pre-production audit that scans a codebase for security, database, deployment, code quality, AI/LLM, dependency, fronte…

Pre-production audit that scans a codebase for security, database, deployment, code quality, AI/LLM, dependency, frontend, and observability issues. Intercepts deploy commands and blocks until critical items pass. Stack-agnostic. Use for "run ship gate", "am I ready to ship", "p…

Claude CodeMedium risk · 中风险$
rating · 评分
14k
stars · 星标
View看详情 →
#6

pr review expert

by alirezarezvani·updated 2mo ago

Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code…

Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.

Claude CodeMedium risk · 中风险$
rating · 评分
14k
stars · 星标
View看详情 →
#7

a11y audit

by alirezarezvani·updated 2mo ago

Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js,…

Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports…

Claude CodeMedium risk · 中风险$
rating · 评分
14k
stars · 星标
View看详情 →
#8

intended-vs-implemented

by phuryn·updated 1mo ago

The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bu

The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy findings. Use when auditing AI-built code, reviewing access control against documented permissions, or checking whether a codebase matches its own documentation.

Claude CodeCodexAutomated screen · 自动筛查$
rating · 评分
13k
stars · 星标
View看详情 →
#9

pr-review

by MiniMax-AI·updated 2mo ago

Review pull requests for the MiniMax Skills repository. Use when reviewing PRs, validating new skill submissions, or che

Review pull requests for the MiniMax Skills repository. Use when reviewing PRs, validating new skill submissions, or checking existing skills for compliance. Run the validation script first for hard checks, then apply quality guidelines for content review. Triggers: PR review, pull request, validate skill, check skill.

Claude CodeCodexAutomated screen · 自动筛查$
rating · 评分
12k
stars · 星标
View看详情 →
#10

pr review

by MiniMax-AI·updated 2mo ago

Review pull requests for the MiniMax Skills repository. Use when reviewing PRs, validating new skill submissions, or ch…

Review pull requests for the MiniMax Skills repository. Use when reviewing PRs, validating new skill submissions, or checking existing skills for compliance. Run the validation script first for hard checks, then apply quality guidelines for content review. Triggers: PR review, p…

Claude CodeCodexAutomated screen · 自动筛查$
rating · 评分
12k
stars · 星标
View看详情 →

Why we didn't pick these为什么没选这些

Also common, but didn't make the picks同样常见,但未入精选
  • autoreview

    Workflows that require stronger human review than this catalog entry documents.

    需要比当前目录条目更严格人工复核的工作流。

  • react-doctor

    Workflows that require stronger human review than this catalog entry documents.

    需要比当前目录条目更严格人工复核的工作流。

  • rails code review

    Workflows that require stronger human review than this catalog entry documents.

    需要比当前目录条目更严格人工复核的工作流。

Didn't find what you need?没看到合适的 skill?

Tell us your pain points and we'll go look.把你的痛点告诉我们,我们会去找。

Skill Market
Find the best AI skills for the job·按品类找最好用的 AI 技能
v0.4 · 1306 skills indexed · last review 2026-06-09