phoenix-cli

Name: phoenix-cli
Availability: InStock
Author: exiao

Fetch and analyze LLM application traces from the Phoenix observability platform.

37|12|Updated Feb 24, 2026

Search Tags:#observability #trace analysis #llm operations #llm debugging #phoenix cli #experiment review

Ready to run

npx skills add https://github.com/exiao/skills --skill phoenix-cli-exiao

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: phoenix-cli
Source: https://github.com/exiao/skills/tree/main/phoenix-cli
Command: npx skills add https://github.com/exiao/skills --skill phoenix-cli-exiao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you debug and understand your LLM applications by providing tools to inspect traces, identify errors, and analyze experiments directly from the command line.

Core Features & Use Cases

Trace Analysis: Fetch and inspect detailed traces of your LLM application's execution.
Error Debugging: Quickly find and diagnose failures within your traces and spans.
Experiment Review: Analyze LLM experiments, including performance and error patterns.
Use Case: You've deployed a new RAG system and users are reporting inconsistent results. Use Phoenix CLI to fetch traces, identify which retrieval or LLM spans are failing, and pinpoint the root cause of the inconsistency.

Quick Start

Use the phoenix-cli skill to fetch the 10 most recent traces for your application.

Frequently Asked Questions about phoenix-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I debug LLM application failures using trace analysis?▼

Trace analysis helps debug LLM application failures by fetching detailed execution traces to identify errors within specific spans. You can inspect these traces directly from the command line to pinpoint the root cause of inconsistent results.

How do I fetch and inspect traces for my LLM app from the command line?▼

You can fetch and inspect LLM app traces from the command line using Phoenix CLI. It enables fetching recent traces, filtering for failures, and supporting raw JSON output for programmatic access and integration with data manipulation tools.

Can I use jq for advanced data manipulation when reviewing LLM experiments?▼

Yes, you can use jq for advanced data manipulation when reviewing LLM experiments. The Phoenix CLI integrates with jq and supports raw JSON output, allowing you to programmatically filter and analyze experiment performance and error patterns.

What is the best way to diagnose inconsistent results in a deployed RAG system?▼

The best way to diagnose inconsistent RAG system results is to fetch execution traces and identify failing retrieval or LLM spans. Using command-line tools to analyze these traces allows you to quickly pinpoint the root cause of the inconsistency.

Does Phoenix CLI support raw JSON output for programmatic access to spans?▼

Yes, Phoenix CLI supports raw JSON output for programmatic access to spans. This allows you to extract trace data and pipe it into other command-line tools for advanced data manipulation and automated debugging workflows.

Why do I need an observability platform to review LLM experiments?▼

You need an observability platform to review LLM experiments because it captures detailed execution traces and spans. Analyzing this data enables you to identify performance bottlenecks, debug failures, and understand error patterns within your application.