Code Review Agent Skills

Review GitHub PRs and GitLab MRs with structured analysis including blast radius, security scanning, test coverage delta, breaking change detection, and performance impact.

Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans.

Automates code review for pull requests across 14+ languages, analyzing complexity, risk, code quality, and generating structured review reports.

Creates persona-targeted, step-by-step CodeTour walkthroughs that link to real files and line numbers for onboarding, architecture, PR review, and more.

Conducts multi-axis code review across correctness, readability, architecture, security, and performance before merging any change.

Provides a structured protocol for receiving and evaluating code review feedback, emphasizing technical verification over performative agreement.

Execute implementation plans by dispatching a fresh subagent per task, with task review after each and a whole-branch review at the end.

Guides completion of development work by verifying tests, detecting the environment, and presenting structured options for merging, creating a PR, or discarding changes.

Provides Vue.js best practices and workflow guidance, including architecture planning, component design, reactivity patterns, and performance optimization for Vue 3 projects.

Split a large pull request into multiple smaller PRs to reduce the number of required CODEOWNERS reviewer groups.

Lint and format Python code for Megatron-LM using ruff, black, isort, pylint, and mypy, with commands for autoformatting and import ordering.

Create CodeTour `.tour` files with persona-targeted, step-by-step walkthroughs anchored to real files and line ranges for onboarding, architecture, PR review, and code explanation.

Forces AI agents to investigate before editing or running destructive commands, improving code quality by requiring concrete facts like importers, data schemas, and user instructions.

Scans source code repositories across C++, Android, iOS, and Web to classify files, detect embedded third-party libraries, and produce actionable four-level verdicts per module with interactive HTML reports.

Create and manage Hookify rules that define patterns to watch for and messages to display when those patterns match.

Enforce idiomatic Rust patterns for ownership, error handling, enums, traits, concurrency, and best practices to build safe, performant applications.

Provides real-time structural code health scores via CodeScene MCP to review code quality before edits, verify score deltas after changes, and gate commits and PRs.

Provides idiomatic React 18/19 patterns for hooks, server/client components, Suspense, error boundaries, forms, data fetching, state management, and accessibility-first composition.

Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable applications.

Enforce idiomatic Kotlin conventions for null safety, immutability, sealed classes, coroutines, extension functions, DSL builders, and Gradle Kotlin DSL.

Provides Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

Trace every user-facing button through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI inconsistent.

Establishes baseline coding conventions for naming, readability, immutability, and code-quality review across projects.

Prevents Ethereum hashing bugs by distinguishing Keccak-256 from Node's NIST SHA3-256, with code examples for ethers, viem, and web3.js.

Organizes 70+ React and Next.js performance optimization rules across 8 priority categories for use when writing, reviewing, or refactoring code.

Guides AI agents through engineering workflows with eval-first execution, task decomposition, cost-aware model routing, and review focus for generated code.

Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.

Provides best practices for implementing authentication, authorization, input validation, CSRF protection, secrets management, rate limiting, and dependency security in Spring Boot services.

Enforces modern, safe, and idiomatic C++ coding practices based on the C++ Core Guidelines for writing, reviewing, or refactoring C++ code.

Scans legacy codebases to extract implicit coding conventions across architecture dimensions, resolves conflicts interactively, and generates an enforceable style rules file.

Interact with GitHub issues, pull requests, Actions runs, and the GitHub API using the `gh` CLI.

Guide for continuous improvement, error proofing, and standardization in code and processes. Use when improving code quality, refactoring, or discussing process improvements.

Move issues and external pull requests through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Structures a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure.

Enforces an algorithm-first discipline: state Big-O, data structure, and algorithm family before writing loops, queries, or recursion to catch O(n²), N+1, and brute-force defaults.