Phoenix Cli

This gives Claude direct command-line access to Arize Phoenix for debugging LLM applications. It's built around a specific workflow: when your instrumented app is misbehaving, you sample traces or spans, write freeform notes about what went wrong (open coding), then group those notes into a structured failure taxonomy with counts (axial coding). Everything gets tagged with a coding annotation identifier so you can query, revert, or share the entire analysis run. The skill knows when to reach for this, it just needs Phoenix running somewhere and will walk you through picking trace vs. span vs. session as your unit of analysis. Honest take: if you're staring at LLM traces wondering what eval to write next, this is the missing structure between raw logs and a principled test suite.

skills.sh installs: 1K
GitHub stars: 41K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add github/awesome-copilot --skill phoenix-cli --agent claude-code

Installs into .claude/skills of the current project.

Files

Phoenix CLI

Invocation

px <resource> <action>                          # if installed globally
npx @arizeai/phoenix-cli <resource> <action>    # no install required

The CLI uses singular resource commands with subcommands like list and get:

px trace list
px trace get <trace-id>
px trace annotate <trace-id>
px trace add-note <trace-id>
px trace-annotations delete
px span list
px span annotate <span-id>
px span add-note <span-id>
px span-annotations delete
px session list
px session get <session-id>
px session annotate <session-id>
px session add-note <session-id>
px session-annotations delete
px dataset list
px dataset get <name>
px project list
px project get <name>
px annotation-config list
px auth status
px profile list
px profile show [name]
px profile create <name>
px profile use <name>
px profile edit <name>
px profile delete <name>

Setup

export PHOENIX_HOST=http://localhost:6006
export PHOENIX_PROJECT=my-project
export PHOENIX_API_KEY=your-api-key  # if auth is enabled

Always use --format raw --no-progress when piping to jq.

Quick Reference

SKILL.md on GitHub

Details

Repository: github.com/github/awesome-copilot
Categories: Backend & APIs, Git & Pull Requests, Code Review & Quality, AI & Agent Building, Debugging, CLI & Terminal
First seen: Apr 16, 2026