What problem does it solve? CopilotKit applications fail in hard-to-trace ways: runtimes that won't connect, agents that never respond, SSE streams that stall, and frontend tools that silently fail. This Skill provides a structured diagnostic workflow with error code catalogs and AG-UI event tracing to pinpoint root causes quickly. ## Core Features & Use Cases - Structured Diagnostic Workflow: A five-step process covering information gathering, error code matching, AG-UI event tracing, root cause identification, and fix verification. - Complete Error Code Catalog: Reference documents covering v1 CopilotKitErrorCode, v2 CopilotKitCoreErrorCode, TranscriptionErrorCode, and Intelligence platform HTTP errors with resolutions. - Quick Diagnostic Workflows: Step-by-step sequences for common scenarios including runtime connectivity, agent not responding, streaming failures, frontend tool issues, and transcription problems. - Use Case: Your CopilotKit chat connects but the agent never replies. Follow the "Agent Not Responding" workflow to check the /info endpoint, inspect the SSE stream for RunErrorEvent, verify the LLM API key, and validate the BuiltInAgent model string. ## Quick Start Ask the assistant to diagnose why your CopilotKit agent is not responding and have it walk through the runtime connectivity and SSE event stream checks.