Code review

Generate copy-pasteable prompts for driving separate Claude Code sessions through refactor, review, or migration work.

pikax/verter

Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance.

rohitg00/skillkit

Reviews a GitHub pull request and drafts a small set of inline comments in a human reviewing voice, each checkable from the line it points at, then posts them after approval.

google/adk-recipes

Record code review findings (GitHub Copilot PR review or a local AI review) that led to a code change in docs/code-review-feedback/ as append-only entries with root-cause analysis.

haru/redmine_ai_helper

Review code changes against project architecture, style, and conventions

woocommerce/woocommerce-android

Grill the user relentlessly about a plan, design, decision, or set of review findings — working the decision tree in rounds until nothing is left silently assumed.

nrwl/nx

Code review covering security, performance, quality and maintainability, with a fixed report layout and two analysis scripts; the SKILL.md itself is in Ukrainian.

luongnv89/claude-howto

Process and hard rules for conducting code reviews in this repo: PRs, branches, commit ranges, and working diffs.

synnaxlabs/synnax

Reviews Nix expressions, NixOS modules and flake.nix files for style, naming, maintainability and extensibility, then runs nix fmt and nix flake check.

Ruixi-rebirth/flakes

Guidance for using the aster CLI to work in a codebase with an AI agent: chat and edit code, run AI code reviews, apply fixes, and manage sessions, memory, and skills.

Zfinix/aster

Prepare for, perform, or tighten code review workflow: PR scope, review checklist, reviewer expectations, and merge hygiene.

managedcode/Storage

Turns the current session's code changes into a Markdown walkthrough shown in a native Glimpse window, with highlighted code, rendered diffs and review feedback.

cashew-labs/libretto

Review changed code against project standards. An agent skill from vectorize-io/hindsight.

vectorize-io/hindsight

Reviews Delphi or Pascal code for memory leaks, invalid object access and swallowed exceptions, reporting only what it finds in a fixed severity format.

gustavoeenriquez/MakerAi

Restructure existing code without changing its behavior, through a test-gated refactoring loop: a named target, a green suite over that target before any edit, a planned sequence of small named…

testdouble/han

Mandatory AI code review before committing in honeybadger-js.

honeybadger-io/honeybadger-js

A skill your agent uses when the user invokes /cr, requests a code review, or before committing to verify correctness, security, and quality of new or modified code in the working tree.

ZhangShenao/harness9

Perform code reviews following Sentry engineering practices.

getsentry/skills

Reviews Java concurrent code for thread safety, race conditions and deadlocks, and for pitfalls with Virtual Threads, CompletableFuture, ExecutorService and Spring @Async.

decebals/claude-code-java

Reviews Handsontable monorepo changes across architecture, code quality, performance and accessibility, and tests, with a confidence rating on every finding.

handsontable/handsontable

Delegate a coding task to the Grok Build CLI as a background implementer, then review its diff and land it yourself.

amElnagdy/delegate-skills

Terrain SDD standardized workflow — requirement clarification, technical design, code generation, and code review.

sopaco/terrain

Opens Plannotator's browser-based review UI for the current worktree, another directory or a pull request URL, then applies the feedback it returns.

backnotprop/plannotator

Deep code review of PR or materialized candidate-patch changes for correctness, safety, and MAUI conventions.

dotnet/maui

Reviews a pull request for idiomatic implementation: use of the language, standard library, ecosystem conventions and the repository's own patterns.

eric-tramel/moraine

Classify Datapages findings by reach and severity and write review-.md reports.

romshark/datapages

When the user asks for a code review, shares code for feedback, or says "review this", "check my code", "what's wrong with this".

shawnpang/startup-founder-skills

A skill your agent uses when reviewing code for bugs, security issues, performance problems, or adherence to best practices.

peintune/runjam

Self-reviews completed work in an agtx-managed task for correctness, edge cases and code quality, fixes issues, commits and writes .agtx/review.md with a status.

fynnfluegge/agtx

收集工作区未提交改动或最近一次提交的 git 变更面，做只读代码审查并给出带文件行号的问题清单。适用：审查改动、检查刚写的代码质量。不修改代码。

iZiTTMarvin/Nova-agent

Mandatory pre-commit validation for every Copilot code review on pull requests in the regle monorepo.

victorgarciaesgi/regle

Review code changes using Hyperlane Explorer coding standards.

hyperlane-xyz/hyperlane-explorer

Generates a self-contained HTML diagram of a code change or architecture, with data flow, file groupings and design decisions, and a copy-as-image button for sharing.

comet-ml/opik

Review code quality, security, and maintainability before committing.

Thank-you-Linus/Linus-Dashboard

A skill your agent uses when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or…

NeoLabHQ/context-engineering-kit

Security-focused source code review and SAST. An agent skill from transilienceai/communitytools.

transilienceai/communitytools

Conduct a thorough code review of the current Git branch or specific files in Megingiard.

stormpanda/megingiard

Senior code review specialist. An agent skill from selmakcby/claude-agents-skills.

selmakcby/claude-agents-skills

Review Langfuse code changes for correctness, regressions, and best practices.

langfuse/langfuse

Review code for refactorability — surface concrete, prioritized refactoring opportunities grounded in Martin Fowler's smell catalog and SOLID, augmented with static analysis tools (gocyclo…

meain/dotfiles

A skill your agent uses when reviewing code, pull requests, patches, CLs, diffs, or proposed implementations for engineering quality, code health, design, functionality, tests, maintainability…

agentara/skills

Code review of current git changes with an expert senior-engineer lens.

serpro69/claude-toolbox

Reviews agent-written changes before merge with a review subagent and evidence-backed findings, plus a fuller adversarial protocol for security and data-loss risk.

manaflow-ai/cmux

Code review with principal-engineer-level depth. An agent skill from Houseofmvps/ultraship.

Houseofmvps/ultraship

Reviews GitHub pull requests with a swarm of specialized agents covering security, performance, architecture, style and accessibility, driven by the gh CLI and ruv-swarm.

ruvnet/agentic-flow

Review a set of code changes against Sculptor's review categories and produce a markdown findings table.

imbue-ai/sculptor

Reviews pull requests that use the fp-go library against its conventions: v2 imports, data-last arguments, point-free style, Result over Either and idiomatic monads.

IBM/fp-go

Covers what to do on opening a pull request and after every push: apply a label, watch CI to green, answer every review comment and escalate real design trade-offs.

pydantic/pydantic-ai