Skip to content
Get packs

Arize Dataset Manager

Create, browse, export and append evaluation datasets in Arize using the ax CLI

Source Download skill
Repository
github/awesome-copilot
Stars
40,703
Licence
MIT
Files
3 files

What it does

Once installed, the agent knows how to work with Arize, a platform for testing AI systems. It can list, look up, create, export and add examples to datasets (collections of test records used to evaluate AI models), by running the ax command-line tool on your behalf. It also includes guidance for troubleshooting login and setup problems.

Great for

  • ML or AI engineers who keep evaluation and golden test sets in Arize
  • Teams that want an agent to export or bulk-load test examples without memorising CLI flags
  • Anyone already using the ax CLI and an Arize account

Skip it if

  • People without an Arize account or API key, since every command needs one (the skill cannot be used without it)
  • Tasks needing datasets stored outside Arize, as the skill only targets Arize spaces
  • Sensitive data exports, since exported examples are written to local files and may contain private content that should not be shared or committed

Try asking

  • “List the datasets in my Arize workspace and show the latest versions”
  • “Export the golden test set 'support-qa' to a local JSON file and check the row count”
  • “Create a new dataset called 'eval-v2' from my examples.csv file”
  • “Append these new question and answer examples to my existing evaluation dataset”
Step-by-step guide: how to use Arize Dataset ManagerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    arize-dataset.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip arize-dataset.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip arize-dataset.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent the dataset name plus the space name or ID so it does not need to ask follow-up questions
  • For datasets with more than 500 examples, ask explicitly for a full export so results are not truncated
  • Review exported files before sharing them, as they may contain user data

What's inside

  • references/ax-profiles.md
  • references/ax-setup.md
  • SKILL.md

Redistributed unmodified from github/awesome-copilot under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.