Arize Annotation

If you're running human review workflows on Arize, you need annotation configs and queues set up before anyone can label anything. This skill handles both: creating label schemas (categorical, continuous, or freeform), managing review queues, and bulk-updating spans with human feedback via the Python SDK. The CLI covers all the CRUD operations, and the docs are explicit about which surfaces labels apply to (spans, dataset examples, experiment outputs, queue items). One thing to note: list flags like annotation-config-id fully replace existing values on update, so you need to pass everything back, not just what changed. Useful when you're setting up labeling pipelines or need programmatic access to review workflows.

Install to Claude Code

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