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.

Install to Claude Code

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