Testing & Debugging for Claude Code

Use this agent for long-running, autonomous multi-step engineering tasks that must be driven to full completion without handing control back early — e.g., "fix this failing test suite and don't stop until every test passes," "implement this feature end-to-end including tests," or "track down this intermittent bug." The agent plans, investigates the codebase (and the web when needed), implements, and rigorously verifies before ending its turn, checking off a visible todo list as it goes. <example

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

Generate systematic troubleshooting documentation with diagnostic procedures, common issues, and automated solutions

>- TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling. Use PROACTIVELY for any TypeScript/JavaScript issues including complex type gymnastics, build performance, debugging, and architectural decisions. If a specialized expert is a better fit, I will recommend switching and stop.

Expert assistant for developing Model Context Protocol (MCP) servers in TypeScript

Detects and removes unused code (imports, functions, classes) across multiple languages. Use PROACTIVELY after refactoring, when removing features, or before production deployment.

Update and modernize project dependencies with comprehensive testing and compatibility checks

Expert in Vercel platform features, edge functions, middleware, and deployment strategies. Use PROACTIVELY for Vercel deployments, performance optimization, and platform configuration.

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.

Web accessibility compliance specialist. Use PROACTIVELY for WCAG compliance audits, accessibility testing, screen reader compatibility, and inclusive design validation.

Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".

Web application security testing workflow for OWASP Top 10 vulnerabilities including injection, XSS, authentication flaws, and access control issues.

Core Web Vitals optimization specialist. Use PROACTIVELY for improving LCP, FID, CLS, and other web performance metrics to enhance user experience and search rankings.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Use this agent when implementing real-time bidirectional communication features using WebSockets, Socket.IO, or similar technologies at scale. Specifically:\\n\\n<example>\\nContext: Building a collaborative editing platform that requires sub-100ms message delivery to thousands of concurrent users.\\nuser: \"I need to implement a WebSocket-based backend for real-time collaboration. We expect 5K concurrent connections with 100 messages per second across all users.\"\\nassistant: \"I'll architect

This skill should be used when the user asks to "analyze network traffic with Wireshark", "capture packets for troubleshooting", "filter PCAP files", "follow TCP/UDP streams", "detect network anomalies", "investigate suspicious traffic", or "perform protocol analysis". It provides comprehensive techniques for network packet capture, filtering, and analysis using Wireshark.

Write comprehensive unit and integration tests with proper mocking and coverage

Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.

Integration with OpenAI Codex CLI for complex code generation and debugging

Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

Perform cohort analysis on user data — retention curves, feature adoption, and engagement trends

Analyze A/B test results — statistical significance, sample size validation, and ship/extend/stop recommendations

Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods. Use when validating assumptions, testing feature ideas cheaply, or planning product experiments.

Design lean startup experiments (pretotypes) for a new product. Creates XYZ hypotheses and suggests low-effort validation methods like landing pages, explainer videos, and pre-orders. Use when validating a new product idea, creating pretotypes, or testing market demand.

Perform cohort analysis on user engagement data — retention curves, feature adoption trends, and segment-level insights. Use when analyzing user retention by cohort, studying feature adoption over time, investigating churn patterns, or identifying engagement trends.

Turn documented intent into a test-coverage map — inventory the tests that exist today, derive use-case cases from the system docs, separate existing coverage from proposed tests and unverified gaps, mark each unit / guarded-live / manual, and recommend a green-before-merge CI gate

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.

Generate realistic dummy datasets for testing — CSV, JSON, SQL inserts, or Python scripts

Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact

Analyze user feedback data to identify segments with sentiment scores, JTBD, and product satisfaction insights. Use when analyzing user feedback at scale, running sentiment analysis on reviews or surveys, or identifying satisfaction patterns.

Turn a vibe-coded repo into a reviewer-ready shipping packet — document the app, wire agent context, run security and performance audits, map test coverage, and compile the results

The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded agents/automation. Defines what each doc must capture and how a reviewer or auditor uses it. Use when documenting a codebase for handoff, mapping user journeys and trust-boundary cross

Generate comprehensive test scenarios from user stories or feature specs — happy paths, edge cases, and error handling

Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writing QA test cases, creating test plans, defining acceptance tests, or preparing for feature validation.

Automate browser interactions using the Browserbase browse CLI. Use when a task requires navigating websites, reading page state, clicking elements, filling forms, or validating browser results with the browse command.