Code Review Skills for AI Agents

Validates that a branch or PR implementation matches introduced product, technical, and security specs, producing a mismatch list and resolving each with the user.

by warpdotdev/common-skills

Go security best practices and vulnerability prevention, with Review and Audit modes covering injection, crypto, secrets, auth, and threat modeling.

by samber/cc-skills-golang

• Security & safety
• Style

Production-ready Go testing guidance: table-driven tests, testify, parallel tests, fuzzing, coverage, and a Review mode for PR test changes.

by samber/cc-skills-golang

• Style

Defensive Go coding against accidental bugs: nil panics, typed-nil interfaces, slice aliasing, integer truncation, and zero-value safety, for writing or reviewing code.

by samber/cc-skills-golang

• Security & safety
• Style

Idiomatic Go design patterns and idioms, with a Review mode that audits existing code for init() abuse, unbounded resources, missing timeouts, and global state.

by samber/cc-skills-golang

• Security & safety
• Style

Go code style conventions covering line breaking, variable declarations, control-flow clarity, and comments, for writing or reviewing Go code.

by samber/cc-skills-golang

• Style

Reviews Swift concurrency code for correctness, modern API usage, and async/await pitfalls, reporting genuine problems with before/after fixes.

by twostraws/swift-concurrency-agent-skill

Adds diff-scoped AI security scanning to CI/CD so every pull request gets a pentest that blocks vulnerable code, with PR comments and SARIF output.

by usestrix/strix

• Security & safety

Needs (stated): Docker

Vercel's React/Next.js performance rule catalog (70 rules across 8 categories) used when writing, reviewing, or refactoring React code for performance.

by vercel-labs/agent-skills

Subjects non-trivial decisions to a fresh-context adversarial review before they stand, stress-testing assumptions and hidden failure modes.

by addyosmani/agent-skills

• Style

Structures git workflow practices: atomic commits, branching, conflict resolution, and opening or reviewing pull requests, plus release/versioning conventions.

by addyosmani/agent-skills

• Style

Interactively walks a user through PR review comments, collects per-comment decisions, makes code changes, then posts replies and resolves threads after approval.

by warpdotdev/common-skills

Guides creating a pull request in the warp repository: merging master, reviewing your own diff, linking tasks, and structuring the PR for effective review.

by warpdotdev/common-skills

• Tests
• Style

A verification system for Claude Code sessions that runs build, type, lint, test, security, and diff-review phases before claiming work is complete.

by affaan-m/ecc

• Tests
• Style

Verification loop for Django projects covering migrations, linting, tests with coverage, security scans, and deployment readiness before release or PR.

by affaan-m/ecc

• Tests
• Security & safety
• Style

Needs (stated): Python

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

by affaan-m/ecc

• Tests
• Style

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

by obra/superpowers

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

by obra/superpowers

> Review and create distinctive, production-grade frontend interfaces with high design quality and design system compliance. Evaluates using three pillars: frictionless insight-to-action, quality craft, and trustworthy building. USE FOR: PR reviews, design reviews, accessibility audits, design system compliance checks, creative frontend design, UI code review, component reviews, responsive design checks, theme testing, and creating memorable UI. DO NOT USE FOR: Backend API reviews, database schema reviews, infrastructure or DevOps work, pure business logic without UI, or non-frontend code.

by microsoft/skills

• Design fit

Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.

by openai/skills

• Security & safety

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.

by openai/skills

• Security & safety

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

by addyosmani/agent-skills

• Complexity

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

by addyosmani/agent-skills

• Correctness

Refactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by extracting helper methods.

by github/awesome-copilot

Go performance optimization patterns and methodology, including a performance code review mode for allocation, CPU, memory, and hot-path issues.

by samber/cc-skills-golang

• Style

Grounds implementation decisions in official documentation, verifying and citing sources before writing or reviewing framework-specific code.

by addyosmani/agent-skills

Needs (stated): Python

Builds, debugs, or reviews Cloudflare Durable Objects code for persistent state and coordination, covering storage, RPC, alarms, and wrangler config.

by cloudflare/skills

Runs managed pentests of web apps, APIs, or repos on the Strix platform, including launching scans, triaging vulnerabilities, and starting PR reviews.

by usestrix/strix

GitHub Actions CI/CD configuration for Go projects, including test, lint, SAST, coverage, and vulnerability-scan jobs plus AI-driven PR review wiring.

by samber/cc-skills-golang

• Style

Spec-driven development using Momentic tests as the contract, writing expected behavior as tests before implementing product changes.

by momentic-ai/skills

Read-only analysis skill for deep learning research repositories: maps model structure, entrypoints, and configs, and flags suspicious implementation patterns without modifying code.

by lllllllama/rigorpilot-skills

Specialized review skill that evaluates animation and motion code against a high craft bar, flagging easing, duration, origin, performance, and a11y issues.

by emilkowalski/skills

Read-only advisor that surveys a codebase's animation code and produces a prioritized audit plus self-contained implementation plans for other agents.

by emilkowalski/skills

>- Transform the agent into a Cloud Solution Architect following Azure Architecture Center best practices. Use when designing cloud architectures, reviewing system designs, selecting architecture styles, applying cloud design patterns, making technology choices, or conducting Well-Architected Framework reviews.

by microsoft/skills

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

by vercel-labs/agent-skills