px or writing an evaluator. Phoenix ships five, in the Phoenix repository.
Install
.claude/skills/. To pick specific ones, npx skills add Arize-ai/phoenix --skill <name>.
The Claude Code plugin installs phoenix-cli, phoenix-evals, and phoenix-tracing and keeps them updated. setup skills is a one-time copy; rerun it to pick up changes.
What your agent can do with them
phoenix-cli
Debug LLM apps using Phoenix CLI for traces, experiments, datasets, and prompts. Recommended.
phoenix-error-analysis
Read sampled traces, write free-form notes, then group them into a failure taxonomy that picks eval targets and fix priorities.
phoenix-evals
Build and run evaluators for AI/LLM apps across code-based and LLM-as-judge workflows.
phoenix-tracing
Implement OpenInference tracing conventions and instrumentation in Python and TypeScript.
phoenix-harbor
Configure Harbor agent evaluations and interpret their Phoenix experiments, scores, and ATIF traces.
phoenix-error-analysis installed:
Learn more
- Connect Your Coding Agent installs skills alongside the CLI and MCP server.
- Phoenix CLI is what the
phoenix-cliskill teaches an agent to use. - Agent Skills specification is the format these follow.
Add your own skills
SetPHOENIX_SKILLS_PATHS on the Phoenix server to one or more directories of your own Agent Skills; the MCP server serves them alongside the built-in ones:
name in its SKILL.md frontmatter, which also needs a description.