phoenix-tracing

Official

Production-grade tracing for Phoenix

AuthorArize-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.

Core Features & Use Cases

  • Standardized OpenInference span semantics for LLM, CHAIN, RETRIEVER, TOOL, GUARDRAIL, and EVALUATOR kinds.
  • Comprehensive guidance linking to Phoenix docs, OpenInference specs, and language-specific references (Python and TypeScript).
  • Production readiness: instrumentation setup, batch processing, and privacy considerations for deployments.

Quick Start

Review SKILL.md and follow the Quick Start to enable Phoenix OpenInference tracing in your Python or TypeScript project.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: phoenix-tracing
Download link: https://github.com/Arize-ai/phoenix/archive/main.zip#phoenix-tracing

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 223,000+ vetted skills library on demand.