Analyze Arize AX traces to debug LLM issues and monitor trace health.
npx skills add https://github.com/stevenmunoz/turbo-ai-exercise --skill arize-traces
Please help me install this Agent Skill. Skill: arize-traces Source: https://github.com/stevenmunoz/turbo-ai-exercise/tree/main/.claude/skills/arize-traces Command: npx skills add https://github.com/stevenmunoz/turbo-ai-exercise --skill arize-traces
Analyzes Arize AX traces to help ML teams diagnose issues, assess observability, and optimize model behavior by surfacing structured trace data, token usage, and health signals.
Run python3 scripts/get_trace.py <trace_id> to visualize the full trace tree for a given trace.
High-intent search queries and answers about installing and using this skill.
To debug LLM traces, you can fetch and visualize the hierarchical trace tree to quickly locate the failing span, inspect its inputs and outputs, and trace the error to its source.
You monitor LLM trace health by aggregating latency, error rates, and token usage across spans to detect anomalies and identify cost spikes in your model behavior.
Yes, this skill analyzes Arize AX traces specifically for projects using Arize for LLM observability, applying to spans and traces to surface structured data and health signals.
The best way to visualize trace trees via CLI is running the get_trace script with a specific trace ID, which displays hierarchical span relationships, timings, models, and status.
Yes, you need Python to run the CLI-based exploration scripts that fetch and visualize traces, with the certifi package required as a dependency for handling SSL certificates.
Arize-aiExport and analyze Arize traces and spans by ID for debugging LLM applications.
tu11aaAdjust crew effort levels to control token usage and agent selection.
RepairYourTechConfigure Datadog for APM, log management, metrics, dashboards, and alerting.
ethan-rioAdd end-to-end tracing and observability to LLM applications via Arize AX.
