skilld
All skills
github avatar

/arize-dataset

@4e136f3 official
by githubgithub/awesome-copilot40k stars
5,040

Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the user needs test data, evaluation examples, or mentions create dataset, list datasets, export dataset, append examples, dataset version, golden dataset, or test set.

Ask your Agent

Use this Skill: https://skilld.dev/gh/github/awesome-copilot/arize-dataset

This session only. Nothing lands on disk.

referencesax-setup.md

≈383 tokens on demand. Your agent reads this file only when SKILL.md points to it.

ax CLI — Troubleshooting

Consult this only when an ax command fails. Do NOT run these checks proactively.

Check version first

If ax is installed (not command not found), always run ax --version before investigating further. The version must be 0.14.0 or higher — many errors are caused by an outdated install. If the version is too old, see Version too old below.

ax: command not found

macOS/Linux:

  1. Check common locations: ~/.local/bin/ax, ~/Library/Python/*/bin/ax
  2. Install: uv tool install arize-ax-cli (preferred), pipx install arize-ax-cli, or pip install arize-ax-cli
  3. Add to PATH if needed: export PATH="$HOME/.local/bin:$PATH"

Windows (PowerShell):

  1. Check: Get-Command ax or where.exe ax
  2. Common locations: %APPDATA%\Python\Scripts\ax.exe, %LOCALAPPDATA%\Programs\Python\Python*\Scripts\ax.exe
  3. Install: pip install arize-ax-cli
  4. Add to PATH: $env:PATH = "$env:APPDATA\Python\Scripts;$env:PATH"

Version too old (below 0.14.0)

Upgrade: uv tool install --force --reinstall arize-ax-cli, pipx upgrade arize-ax-cli, or pip install --upgrade arize-ax-cli

SSL/certificate error

  • macOS: export SSL_CERT_FILE=/etc/ssl/cert.pem
  • Linux: export SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt
  • Fallback: export SSL_CERT_FILE=$(python -c "import certifi; print(certifi.where())")

Subcommand not recognized

Upgrade ax (see above) or use the closest available alternative.

Still failing

Stop and ask the user for help.

Source: SKILL.md on GitHub

Third-party checks

1 warning16d4 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill is well-designed with strong security practices for credential handling, but it is classified as low risk due to its role in processing external data files and modifying shell configuration files for persistence.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: MEDIUM · 1 issue

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 4e136f3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 5 months ago

Capability

metadata
{
  "author": "arize",
  "version": "1.0"
}
compatibility
Requires the ax CLI and a configured Arize profile.

Topics

README badge

README badge for github/awesome-copilot/arize-dataset

What it does

Manages datasets in Arize for evaluation and testing via the ax CLI. Supports creating datasets from CSV/JSON/Parquet files, appending examples, exporting data, listing versions, and querying metadata — all keyed by dataset name or ID within a space.

Generated from the current SKILL.md.

Frequently asked

Does this skill work with datasets larger than 500 examples?
Yes. By default, export is limited to 500 examples, but the `--all` flag enables unlimited bulk export for larger datasets. If an export returns exactly 500 examples, re-run with `--all` to ensure you get the full dataset.
What file formats can I use to create or append datasets?
CSV, JSON, JSONL, and Parquet are supported. CSV and JSON are most common; JSONL expects one object per line (not a JSON array), and Parquet preserves column types. You can also pipe data via stdin using `--file -` instead of creating a temp file.
Do I need to specify the space when working with datasets?
Only when using a dataset name instead of its ID. If you pass a dataset ID, the `--space` flag is optional. The space name or base64 ID can be found with `ax spaces list`.
What happens if I append examples with field names that don't match existing examples?
New field names are silently added as new columns, and missing fields become null. Typos in field names create unintended columns, so verify field names match before appending by exporting a sample example and comparing keys.
How do I troubleshoot authentication errors?
Run `ax profiles show` to check your current profile and API key. If credentials are missing or invalid, update your profile with `ax profiles` or get your API key from https://app.arize.com/admin > API Keys. Never read `.env` files for credentials.

Generated from the current SKILL.md. These answers refresh after source changes.