Best code review skills, page 6

Builds a skeptical reviewer grounded in the codebase and research notes to try to refute a spec before any code is written, citing file:line evidence and ending in a go or no-go gate.

JuliusBrussee/cavekit

Collects every review comment on a pull request, checks each against the real code, fixes the valid ones, pushes, and replies on and resolves each thread.

stickerdaniel/linkedin-mcp-server

A skill your agent uses when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final…

cnfjlhj/ai-collab-playbook

Gatekeeps GitHub issues and pull requests for Qwen Code maintainers through staged static reviews that post a comment after each stage, under strict safety rules.

QwenLM/qwen-code

Evidence-first review of Pimcore pull requests — judge against a fixed review contract, hold fixes to the Pimcore quality bar, and enforce the house PHP coding guidelines.

pimcore/data-hub

Review code for quality, correctness, and security vulnerabilities.

hiroshiyui/GuilelessBopomofo

为 CodeNote Helper 生成普通开发、修复、验证、治理、文档和审核友好类中文执行 prompt。用于把一次具体任务整理成可直接交给 Codex 或 Agent 执行的 prompt；不承载 Plan mode prompt、code review prompt 或项目 skill creator 的完整职责。

Philip-Cao-9527/code-note-helper

Code quality review — identify patterns, anti-patterns, and improvements.

hardness1020/Leeway

Runs the Greptile CLI on the current local branch, fixes what the review finds, and reviews again, until the review comes back 5/5 with zero comments.

galfrevn/apollo

Runs one read-only reviewer subagent per configured model against a diff to challenge a change, then synthesizes a single verdict without applying any fixes.

cursor/plugins

Tracks open pull requests and records CI state, staleness, merge conflicts and unanswered review comments in a state file, then lists the top three actions for a human.

cobusgreyling/loop-engineering

End-to-end workflow for resolving a GitHub issue in astro-mermaid — triages complexity, then runs brainstorm → TDD → implement → docs/spec → code review at the right depth.

joesaby/astro-mermaid

Reviews only the code changed since the last commit, using a code-graph MCP server to find risk-scored changes, test gaps and the blast radius, then writes a short report.

tirth8205/code-review-graph

Run a design-challenging Claude Code review of local git changes in this repository.

sendbird/cc-plugin-codex

Comprehensive code review with security and performance checks

timwuhaotian/the-pair

Review The Holy Qur'an app code against the project's own conventions — layering (UI → Bloc → Repo → DataProvider), bloc anatomy, Provider tier, configs tokens, class widgets, Hive typeId safety…

mhmzdev/the-holy-quran-app

Review VotingPlugin pull requests, branch diffs, commits, and explicitly included local changes before publishing.

BenCodez/VotingPlugin

Audit mobile App PRD/Figma/local-source consistency across page routes, KMP/Clean Architecture, components, analytics, i18n, engineering quality, and industry lenses before runtime validation; use…

leo-kuang-ai/spec-first

Review code against CLAUDE.md standards with focus on multi-chain safety, BigInt precision, and config separation.

morpho-org/morpho-blue-liquidation-bot

Plan-first, one-time human plan approval; batched execution in either Gated (human confirms between batches) or Auto-loop (continuous run after plan approval); strict task-state updates; automatic…

AlephantAI/AIephant-AI-Agent-Gateway

Review code changes for bugs, regressions, convention violations, and high-value cleanup opportunities.

kairyou/agent-tools

Socratic coding tutor powered by GitHub Copilot. An agent skill from timothywarner/chatgptclass.

timothywarner/chatgptclass

Deep EVM smart contract security audit system. An agent skill from austintgriffith/ethskills.

austintgriffith/ethskills

Review a GitHub pull request by summarizing its diff and key design decisions.

NVIDIA/OpenShell

Standalone code review methodology for structured, severity-classified code assessment

josstei/maestro-orchestrate

Audit Grix diffs and pull requests for correctness, regressions, security, lifecycle safety, and cross-component contract consistency.

askie/grix

Runs parallel review agents over a branch, chosen paths or a whole project and merges their findings into one numbered report you can act on by id.

VeryGoodOpenSource/vgv-wingspan

Reviews SGLang changes the way its maintainers do, drawing on a bundled corpus of public PR review threads and a flowchart of how the diff runs.

BBuf/AI-Infra-Auto-Driven-SKILLS

Gives Chinese-language templates and priority labels for code review feedback, plus guidance on bilingual comments, commit messages and common team anti-patterns.

jnMetaCode/superpowers-zh

Reviews a diff or pull request for correctness by reading the callers and contracts around the change, then ranks line-anchored findings and gives a merge-risk verdict.

codewhale-hq/Codewhale

Acts as a skeptical checker for changes an implementer sub-agent made, running the tests, confirming the diff scope and returning approve, reject or escalate to a human.

cobusgreyling/loop-engineering

Perform code reviews (CR) for changed files in the current repository.

Hyk260/PureChat

Finds what a code change could break outside its diff and proves the single fact that makes it safe by running real code instead of writing an explanation.

cursor/plugins

Reviews pull requests in this repository for the defect classes a mechanical checklist misses: documentation that outlived the code it describes, reaction and retry state that leaks or clobbers a…

sortie-ai/sortie

Operate recurring Bangle.io agent follow-ups after a thread has already started.

bangle-io/bangle-io

Runs three parallel reviewers on a diff or branch, one blind, one design-aware and one matching past bug patterns, then triages their findings.

ben-manes/caffeine

Review pull requests, diffs, and code changes in z-shell repositories against the bundled organization criteria and the repository's own contracts and checks, verifying each finding before reporting…

z-shell/zsh-eza

Provides comprehensive code review guidance for React 19, Vue 3, Rust, TypeScript, Java, Python, and C/C++.

andrew-yangy/gru-ai

Performs an architectural review of code against coding standards, SOLID, testability and performance, and reports no verdict when the inputs are missing.

Donchitos/Claude-Code-Game-Studios

Post a single consolidated PR review with summary and inline comments.

hyperlane-xyz/hyperlane-explorer

Tests a security patch against the original bug, its variants and normal behavior, with reproducible baseline-versus-patched evidence before you merge or call it fixed.

trailofbits/skills

Review changes in clickhouse-java for correctness, compatibility, API stability, and missing tests.

ClickHouse/clickhouse-java

Reviews a pull request like a strict senior engineer and posts one consolidated GitHub review, backing every comment with a verified file citation or an official source.

tech-leads-club/agent-skills

Automated code review bash script for SWPM. An agent skill from deinsoftware/swpm.

deinsoftware/swpm

Lists open pull requests in dotnet/maui and dotnet/docs-maui that are worth reviewing next, ranked by priority labels, milestone and partner or community origin.

dotnet/maui

审查当前 git 变更、PR、提交范围、技能定义文件、架构调整或安全敏感代码时使用。输出结构化 Review Gate 结论（Pass/Reject）、问题分级（blocker/warning/suggest）、最低验证矩阵、证据链与复查基线。覆盖正确性、安全、架构、SOLID、可删除代码、性能、异常处理与测试风险；默认只输出 review，不直接修改代码。用户提到 review、code…

CaoMeiYouRen/caomei-auth

用于当前项目的 Claude 代码审查与评分。适用于“代码审查、PR/MR review、质量评分、风险评估”等任务，按 v2.0 规范输出 P0/P1/P2、总分、星级和合并结论，并且终端结果与落盘报告都必须使用中文，结果写入根目录 code-review 文件夹。

LAIJiangFeng/resume-builder

Multi-agent, browser-driven QA pass over a branch or PR — scope it, plan it, fan out one subagent per testing area in its own isolated sandbox, compile a severity-ranked markdown report.

Kiln-AI/Kiln