---
title: "Arize Evaluator Skill - Air Market"
description: "Judging whether an AI's answers are good is hard to do by hand at any volume. This sets up evaluators that use a model as the judge, runs them over your recorded output or your experiments, and keeps…"
canonical: "https://airmarket.ai/app/arize-evaluator"
---

[Air Market](/) / [Data & Analytics](/category/data) / Arize Evaluator Skill

Skill by [GitHub](/@github)

# Arize Evaluator Skill

Have a model grade your model's answers, and keep it grading

## What this does

Judging whether an AI's answers are good is hard to do by hand at any volume. This sets up evaluators that use a model as the judge, runs them over your recorded output or your experiments, and keeps them running on an ongoing basis. Reach for it when you want a repeatable read on quality.

### Top 3 things it does for you

- Set up an LLM judge for your output
- Score spans or an experiment
- Map columns so an evaluator reads the right fields

## Information

**Arize Evaluator Skill at a glance**

|  |  |
| --- | --- |
| Kind | Skill |
| Publisher | [GitHub](/@github) |
| Category | [Data & Analytics](/category/data) |
| Works with | Agent Skills - an open standard supported by 40+ agents |
| Version | 1.0 |
| Size | 38 KB |
| Licence | MIT |
| Repository | [github/awesome-copilot](https://github.com/github/awesome-copilot/tree/97cc3f24602b6431b82dbce2afec7a1f3611664f/skills/arize-evaluator) |
| GitHub stars | 38,187 (as of Nov 2026) |
| Installs | 1,096, counted by skills.sh (Nov 2026) |

## Security report

**Verified.** AIR scanned this exact version of Arize Evaluator Skill and flagged nothing. AIR's verdict: **safe**.

**What Arize Evaluator Skill's check was run against**

|  |  |
| --- | --- |
| Commit | 97cc3f24602b6431b82dbce2afec7a1f3611664f |
| Content hash | 87b5f949a5dd3427fa92e93fc54f5be1acc83d3cb9f1d252353b9a0b5be4944e |
| Files read | [Browse the files at this exact commit](https://github.com/github/awesome-copilot/blob/97cc3f24602b6431b82dbce2afec7a1f3611664f/skills/arize-evaluator/SKILL.md) |

A scan is named by the exact content it read, not by a version number. A different version is a different artifact, and nothing here applies to a version AIR has not scanned.

[Read the full security report for Arize Evaluator Skill](/security/arize-evaluator)

## About Arize Evaluator Skill

This handles LLM-as-judge evaluation workflows on Arize: creating and updating evaluators, running evaluations over spans or experiments, managing the tasks behind them, trigger-run operations, and column mapping.

It also covers continuous monitoring, so evaluation keeps running rather than being a one-off, and improving an evaluator's own prompt.

Reach for it around creating an evaluator or LLM judge, checks like hallucination, faithfulness, correctness or relevance, running an eval, scoring spans or an experiment, or setting up column mapping.

## What's inside

- SKILL.md - instructions
- references/ax-profiles.md - reference
- references/ax-setup.md - reference

## Questions

### Is Arize Evaluator Skill safe to install?

AIR scanned this exact version of Arize Evaluator Skill and flagged nothing. AIR's verdict: safe. The verdict is named by the content that was read, at commit 97cc3f24602b, so it cannot drift onto a version nobody scanned. The full report is at https://airmarket.ai/security/arize-evaluator.

### How do I install Arize Evaluator Skill?

Open https://airmarket.ai/app/arize-evaluator on Air Market and use the install action: Air Market hands Claude a prompt naming this exact skill, and Claude sets it up. Source, pinned to the exact commit this listing describes: https://github.com/github/awesome-copilot/tree/97cc3f24602b6431b82dbce2afec7a1f3611664f/skills/arize-evaluator. Install from that link, not the branch.

## Related on Air Market

- [More Data & Analytics listings](/category/data)
- [Everything by GitHub](/@github)

---

Canonical URL: <https://airmarket.ai/app/arize-evaluator>