Arize Dataset

Manages Arize datasets through the ax CLI. Creates datasets from CSV, JSON, JSONL, or Parquet files, exports examples with automatic pagination for large sets, and appends new records to existing collections. Useful when you need golden datasets for LLM evaluation, want to version test cases, or need to pull production data into experimentation workflows. The export command has a 500 example default limit that truncates silently, so watch for that and use the all flag for complete dumps. Requires a configured Arize profile with API key, which you set up through ax profiles rather than environment variables.

skills.sh installs: 1.1K
GitHub stars: 41K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add github/awesome-copilot --skill arize-dataset --agent claude-code

Installs into .claude/skills of the current project.

Files

Arize Dataset Skill

SPACE — All --space flags and the ARIZE_SPACE env var accept a space name (e.g., my-workspace) or a base64 space ID (e.g., U3BhY2U6...). Find yours with ax spaces list.

Concepts

Dataset = a versioned collection of examples used for evaluation and experimentation
Dataset Version = a snapshot of a dataset at a point in time; updates can be in-place or create a new version
Example = a single record in a dataset with arbitrary user-defined fields (e.g., question, answer, context)
Space = an organizational container; datasets belong to a space

System-managed fields on examples (id, created_at, updated_at) are auto-generated by the server -- never include them in create or append payloads.