arize-dataset

Manage versioned ML evaluation datasets in Arize via the ax CLI.

Updated May 5, 2026
One-click install
npx skills add https://github.com/ethan-rio/skills --skill arize-dataset-ethan-rio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: arize-dataset
Source: https://github.com/ethan-rio/skills/tree/main/skills/arize/arize-dataset
Command: npx skills add https://github.com/ethan-rio/skills --skill arize-dataset-ethan-rio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Manually creating, versioning, and managing ML evaluation datasets in Arize is time-consuming and prone to errors like field mismatches or truncated exports, this skill automates those workflows using the official ax CLI.

Core Features & Use Cases

  • Full Dataset CRUD: Create, list, get, update, and delete Arize datasets directly from your workflow.
  • Bulk Example Management: Append examples from files or inline JSON, export full datasets for offline analysis, and annotate examples in bulk.
  • Use Case: ML engineers running model evaluation cycles can use this skill to quickly spin up golden test datasets, add new evaluation examples after model updates, and export results for reporting without memorizing complex ax CLI flags.

Quick Start

Use the arize-dataset skill to create a new evaluation dataset named 'customer-support-eval' from the provided test examples CSV file and confirm it appears in your Arize space.

Frequently Asked Questions about arize-dataset

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate Arize dataset versioning for ML evaluation?

Arize dataset versioning is automated by wrapping the official ax CLI to handle test dataset creation, updates, and version control directly within ML evaluation workflows. This prevents manual field mismatches and streamlines model evaluation cycles.

How do I append bulk examples to an Arize test dataset?

You can append bulk examples to an Arize test dataset by importing them directly from files or inline JSON. This allows ML engineers to quickly add new evaluation examples after model updates without memorizing complex CLI flags.

Can I export full ML evaluation datasets from Arize for offline analysis?

Yes, full ML evaluation datasets can be exported from Arize for offline analysis and reporting. The skill manages bulk data extraction securely through the ax CLI, preventing truncated exports and ensuring complete dataset retrieval.

What is the best way to annotate ML evaluation examples in Arize?

The best way to annotate ML evaluation examples in Arize is through bulk annotation workflows that apply labels across multiple records. This automates example annotation directly within your pipeline using the ax CLI.

Do I need the ax CLI to manage Arize datasets programmatically?

Yes, the ax CLI is required as it serves as the underlying interface for all dataset interactions. The skill integrates with the ax CLI to perform CRUD operations, schema validation, and secure credential handling for Arize datasets.