🧪 Phoenix Evals
This skill helps you build and run AI evaluators with Phoenix, combining code-first evaluators and LLM nuance for robust validation.
npx playbooks add skill arize-ai/phoenix --skill phoenix-evals
About Phoenix Evals
The Phoenix Evals skill is used for building and running AI evaluators with Phoenix, combining code-first evaluators and large language model nuance to provide robust validation. It enables developers to create and execute tests that leverage both code-based and AI-driven approaches to validation. Developers would use Phoenix Evals when they need to thoroughly validate their code and require a testing solution that integrates the strengths of both code-first and AI-based evaluation methods.
Its 20-word system prompt specializes your agent in testing & qa with structured methodology and proven output formats. Install with one command to activate immediately.
Use Cases
- Writing unit, integration, and end-to-end tests
- Setting up test coverage and CI pipelines
- Refactoring legacy code with confidence using tests
- Creating test plans and QA checklists
Example Prompts
System Prompt (20 words)
This skill helps you build and run AI evaluators with Phoenix, combining code-first evaluators and LLM nuance for robust validation.
Frequently Asked Questions
What is Phoenix Evals?
Phoenix Evals is a free testing & qa skill for AI coding agents. This skill helps you build and run AI evaluators with Phoenix, combining code-first evaluators and LLM nuance for robust validation.. It provides a specialized system prompt that configures your agent with testing & qa expertise.
How do I use Phoenix Evals with Claude Code?
Run npx playbooks add skill arize-ai/phoenix --skill phoenix-evals in your terminal to install Phoenix Evals into your Claude Code session. It works immediately after installation.
Which AI coding agents work with Phoenix Evals?
Phoenix Evals is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Is Phoenix Evals free to use?
Yes, Phoenix Evals is completely free and open source. The full source is available on GitHub at https://github.com/arize-ai/phoenix/tree/main/skills/phoenix-evals. You only need a subscription to the AI agent you use it with.
