Testing & Debugging for Claude Code

Install and configure the Manifest observability plugin for your agents. Use when setting up telemetry, configuring API keys or endpoints, troubleshooting plugin connection issues, or verifying the observability pipeline is running.

Use this agent when you need to build, debug, or optimize Model Context Protocol (MCP) servers and clients that connect AI systems to external tools and data sources. Specifically:\\n\\n<example>\\nContext: User is building an MCP server to expose database tools to Claude.\\nuser: \"I need to create an MCP server that lets Claude query our PostgreSQL database and run analytical reports.\"\\nassistant: \"I'll use the mcp-developer agent to build a production-ready MCP server with proper schema va

MCP server testing and quality assurance specialist. Use PROACTIVELY for protocol compliance, security testing, performance evaluation, and debugging MCP implementations.

Migrate JavaScript project to TypeScript with proper typing and tooling setup

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

AI model evaluation and benchmarking specialist. Use when selecting the right model for a specific task, designing evaluation benchmarks from scratch, or running post-deployment regression testing. Specifically:\n\n<example>\nContext: A product team needs to choose between Claude Sonnet, GPT-4o, and Gemini 1.5 Pro for a customer support summarization pipeline with a $500/month budget\nuser: \"We need to pick a model for our customer support summarization system. We process 50k tickets/month and

Elite bug-fixing agent that enriches task context from Monday.com platform data. Gathers related items, docs, comments, epics, and requirements to deliver production-quality fixes with comprehensive PRs.

Run Monte Carlo simulations with probability distributions, confidence intervals, and statistical analysis

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.

Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with webhook data in workflows.

Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, or the validation loop process.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

Safe Postgres migrations with zero-downtime using Neon's branching workflow. Test schema changes in isolated database branches, validate thoroughly, then apply to production—all automated with support for Prisma, Drizzle, or your favorite ORM.

Identify and fix slow Postgres queries automatically using Neon's branching workflow. Analyzes execution plans, tests optimizations in isolated database branches, and provides clear before/after performance metrics with actionable code fixes.

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.

Test and validate Next.js API routes with comprehensive test scenarios

Comprehensive Next.js migration assistant for Pages Router to App Router, JavaScript to TypeScript, and modern patterns

Comprehensive Next.js performance audit with actionable optimization recommendations

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

Build production-ready monitoring, logging, and tracing systems. Implements comprehensive observability strategies, SLI/SLO management, and incident response workflows.

OCR pipeline validation specialist. Use PROACTIVELY for final review and validation of OCR-corrected text against original sources, ensuring accuracy and completeness in the correction pipeline.

Lab automation platform for Flex/OT-2 robots. Write Protocol API v2 protocols, liquid handling, hardware modules (heater-shaker, thermocycler), labware management, for automated pipetting workflows.

Comprehensive memory usage optimization with leak detection, garbage collection tuning, and memory profiling

Validate Product as Code project structure and files for PAC specification compliance

Responds to PagerDuty incidents by analyzing incident context, identifying recent code changes, and suggesting fixes via GitHub PRs.

Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation.

Perform penetration testing and vulnerability assessment on application

Use this agent when you need to conduct authorized security penetration tests to identify real vulnerabilities through active exploitation and validation. Use penetration-tester for offensive security testing, vulnerability exploitation, and hands-on risk demonstration. Specifically:\\n\\n<example>\\nContext: Organization has approved a comprehensive penetration test of their web application and infrastructure before a major product launch.\\nuser: \"We need a full penetration test of our web ap

Comprehensive performance audit with metrics, bottleneck identification, and optimization recommendations

Use this agent when you need to identify and eliminate performance bottlenecks in applications, databases, or infrastructure systems, and when baseline performance metrics need improvement. Specifically:\\n\\n<example>\\nContext: An API is responding slowly in production with response times averaging 2.5 seconds, and users are complaining about lag.\\nuser: \"We're seeing slow API response times. Can you help identify what's causing the bottleneck?\"\\nassistant: \"I'll profile the application,

Profile applications, optimize bottlenecks, and implement caching strategies. Handles load testing, CDN setup, and query optimization. Use PROACTIVELY for performance issues or optimization tasks.

Identifies and fixes performance bottlenecks in code, databases, and APIs. Measures before and after to prove improvements.

Performance analysis and optimization specialist. Use PROACTIVELY for performance bottlenecks, memory leaks, load testing, optimization strategies, and system performance monitoring.

Performance profiling principles. Measurement, analysis, and optimization techniques.

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.