---
title: "Arize Experiment Skill - Air Market"
description: "You have two versions of something and an opinion about which is better. This runs experiments on Arize and compares the results, so the answer comes from a measurement instead of a feeling. Reach fo…"
canonical: "https://airmarket.ai/app/arize-experiment"
---

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

Skill by [GitHub](/@github)

# Arize Experiment Skill

Settle which version is actually better with a run, not a hunch

## What this does

You have two versions of something and an opinion about which is better. This runs experiments on Arize and compares the results, so the answer comes from a measurement instead of a feeling. Reach for it when choosing between models or checking whether a change actually helped.

### Top 3 things it does for you

- Set up and run an experiment
- Compare how two models performed
- Export the runs for a closer look

## Information

**Arize Experiment 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 | 24 KB |
| Licence | MIT |
| Repository | [github/awesome-copilot](https://github.com/github/awesome-copilot/tree/97cc3f24602b6431b82dbce2afec7a1f3611664f/skills/arize-experiment) |
| GitHub stars | 38,187 (as of Nov 2026) |
| Installs | 1,072, counted by skills.sh (Nov 2026) |

## Security report

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

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

|  |  |
| --- | --- |
| Commit | 97cc3f24602b6431b82dbce2afec7a1f3611664f |
| Content hash | a103a2da6e3ccc02ebf6c131279836c033dd928bd731178a97bac15d09b61b63 |
| Files read | [Browse the files at this exact commit](https://github.com/github/awesome-copilot/blob/97cc3f24602b6431b82dbce2afec7a1f3611664f/skills/arize-experiment/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 Experiment Skill](/security/arize-experiment)

## About Arize Experiment Skill

This creates, runs and analyses Arize experiments for evaluating and comparing model performance, using the ax CLI.

It covers experiment CRUD, exporting runs, comparing results, and the evaluation workflows around them.

Reach for it when you are creating or running an experiment, comparing models, looking at model performance or experiment results, benchmarking, A/B testing models, or measuring accuracy.

## What's inside

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

## Questions

### Is Arize Experiment Skill safe to install?

AIR scanned this exact version of Arize Experiment 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-experiment.

### How do I install Arize Experiment Skill?

Open https://airmarket.ai/app/arize-experiment 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-experiment. 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-experiment>