arize-traces

Community

Debug LLM traces and trace health at a glance

Authorstevenmunoz
Version1.0.0
Installs0

System Documentation

What problem does it solve?

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.

Core Features & Use Cases

  • Trace exploration: fetches and visualizes traces, showing hierarchical span relationships, timings, models, and status.
  • Health and cost insight: aggregates latency, error rates, and token usage for LLM spans to detect anomalies and cost spikes.
  • Use Case: Imagine you are debugging an failing LLM call; this skill helps you quickly locate the failing span, inspect inputs/outputs, and trace the error to its source.

Quick Start

Run python3 scripts/get_trace.py <trace_id> to visualize the full trace tree for a given trace.

Dependency Matrix

Required Modules

certifi

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: arize-traces
Download link: https://github.com/stevenmunoz/turbo-ai-exercise/archive/main.zip#arize-traces

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.