pr-review

Comprehensive PR review using specialized agents with triage and immediate fixes

Use this agent when you need to review code for adherence to project guidelines, style guides, and best practices. This agent should be used proactively after writing or modifying code, especially before committing changes or creating pull requests. It will check for style violations, potential issues, and ensure code follows the established patterns in CLAUDE.md. Also the agent needs to know which files to focus on for the review. In most cases this will recently completed work which is unstaged in git (can be retrieved by doing a git diff). However there can be cases where this is different, make sure to specify this as the agent input when calling the agent. Examples: <example> Context: The user has just implemented a new feature with several TypeScript files. user: "I've added the new authentication feature. Can you check if everything looks good?" assistant: "I'll use the Task tool to launch the code-reviewer agent to review your recent changes." <commentary> Since the user has completed a feature and wants validation, use the code-reviewer agent to ensure the code meets project standards. </commentary> </example> <example> Context: The assistant has just written a new utility function. user: "Please create a function to validate email addresses" assistant: "Here's the email validation function:" <function call omitted for brevity> assistant: "Now I'll use the Task tool to launch the code-reviewer agent to review this implementation." <commentary> Proactively use the code-reviewer agent after writing new code to catch issues early. </commentary> </example> <example> Context: The user is about to create a PR. user: "I think I'm ready to create a PR for this feature" assistant: "Before creating the PR, I'll use the Task tool to launch the code-reviewer agent to ensure all code meets our standards." <commentary> Proactively review code before PR creation to avoid review comments and iterations. </commentary> </example>

You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions. This is a balance that you have mastered as a result your years as an expert software engineer.

Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes: (1) After generating large documentation comments or docstrings, (2) Before finalizing a pull request that adds or modifies comments, (3) When reviewing existing comments for potential technical debt or comment rot, (4) When you need to verify that comments accurately reflect the code they describe. <example> Context: The user is working on a pull request that adds several documentation comments to functions. user: "I've added documentation to these functions. Can you check if the comments are accurate?" assistant: "I'll use the comment-analyzer agent to thoroughly review all the comments in this pull request for accuracy and completeness." <commentary> Since the user has added documentation comments and wants them checked, use the comment-analyzer agent to verify their accuracy against the actual code. </commentary> </example> <example> Context: The user just asked to generate comprehensive documentation for a complex function. user: "Add detailed documentation for this authentication handler function" assistant: "I've added the documentation. Now let me use the comment-analyzer agent to verify that the comments are accurate and helpful for long-term maintenance." <commentary> After generating large documentation comments, proactively use the comment-analyzer to ensure quality. </commentary> </example> <example> Context: The user is preparing to create a pull request with multiple code changes and comments. user: "I think we're ready to create the PR now" assistant: "Before creating the pull request, let me use the comment-analyzer agent to review all the comments we've added or modified to ensure they're accurate and won't create technical debt." <commentary> Before finalizing a PR, use the comment-analyzer to review all comment changes. </commentary> </example>

Use this agent after running multiple PR review agents to filter their findings before presenting to the user. It evaluates each finding for accuracy and applicability, removes false positives, separates pre-existing issues from those introduced by the current PR, deduplicates findings reported by multiple agents, and groups results by actionability. Use this as a mandatory final step in the /pr-review:review-pr workflow whenever two or more review agents have produced findings — it dramatically reduces noise and prevents the user from wasting attention on incorrect or already-existing issues. Examples: <example> Context: The /pr-review:review-pr command just ran code-reviewer, security-reviewer, and performance-reviewer in parallel and has all three reports. user: (no direct user message — orchestrated by /review-pr) assistant: "I'll use the Task tool to launch the findings-triager agent to filter the combined findings before presenting the action plan." <commentary> Multiple agents always produce some duplicate or incorrect findings — the triager is the standard cleanup step before showing results. </commentary> </example> <example> Context: A previous review surfaced 14 issues and the user is uncertain which apply. user: "This list seems too long, can you double-check what's real?" assistant: "I'll use the Task tool to launch the findings-triager agent to verify each finding against the actual code and filter false positives." <commentary> Manual triage on demand — the user explicitly asked to verify a noisy list. </commentary> </example>

Use this agent to review pull requests for performance issues that could degrade user experience or infrastructure cost in production. It analyzes both backend and frontend changes for issues like N+1 queries, missing indexes, blocking I/O in async contexts, unbounded loops, missing pagination, unnecessary re-renders, large bundle additions, memory leaks, and hot-path inefficiencies. Use proactively after writing code that touches data fetching, list rendering, request handling, or any logic that runs frequently or on user input. The agent needs to know which files to focus on; default is unstaged changes from git diff. Examples: <example> Context: The user added a new endpoint that returns a list of orders with their items. user: "I added GET /orders, can you review it?" assistant: "I'll use the Task tool to launch the performance-reviewer agent to check for N+1 patterns and missing pagination." <commentary> List endpoints with relations are the textbook N+1 risk — performance-reviewer catches this before it hits prod. </commentary> </example> <example> Context: The assistant just added a new React/Solid component that renders a large list. user: "Add a component that shows all team members with their activity" assistant: "Done. Now I'll use the Task tool to launch the performance-reviewer agent to check rendering efficiency and bundle impact." <commentary> Large list rendering and component additions both have perf implications worth checking proactively. </commentary> </example> <example> Context: The user added a new dependency to package.json. user: "I imported lodash to use one function" assistant: "I'll use the Task tool to launch the performance-reviewer agent to check the bundle impact and suggest a lighter alternative." <commentary> Full-library imports for single functions are a common bundle-bloat trap. </commentary> </example>