Testing

A tool that helps write, review, or debug code using AI.

Design comprehensive benchmarking protocols for evaluating AI models across multiple dimensions including reasoning, creativity, coding, and safety with reproducible methodologies.

Self-directed debugging skill that systematically reproduces, diagnoses, and fixes bugs with minimal supervision. Uses test-driven verification to ensure fixes actually resolve issues without introducing regressions.

Reference / test server with prompts, resources, and tools

An AI-native code editor built on VS Code with strong agentic features.