arize-skills
Enables teams to programmatically access Arize observability data—datasets, experiments, and traces—directly from CLI workflows, reducing manual hand-offs an…
Skills that guide AI coding agents through Arize LLM-observability workflows: add tracing and instrumentation to your app, export and analyze traces and spans, run experiments, and optimize prompts via the ax CLI. Works with Claude Code, Cursor, Codex, and 40+ other agents; supports cloud and on-prem Arize.
- Agent retrieves experiment baseline metrics for model comparison decisions
- Automated trace inspection to diagnose model inference failures
- Agent queries dataset statistics to validate training data drift
Enables teams to programmatically access Arize observability data—datasets, experiments, and traces—directly from CLI workflows, reducing manual hand-offs and accelerating ML debugging and validation cycles.
ML engineers and data scientists managing production model monitoring and requiring automated access to Arize experiment and trace data.
https://github.com/Arize-ai/arize-skills
By Arize-ai
How to Get It
In Claude Code: /plugin marketplace add Arize-ai/arize-skills then /plugin install arize-skills@arize-skills (or: npx skills add Arize-ai/arize-skills)
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me agent retrieves experiment baseline metrics for model comparison decisions
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Auto-assessment from April sweep — baseline scores pending hands-on review.
2026-04-18: Approved in April sweep: New and small but has a clear description and recent commits — worth tracking.
Things to check
- Requires active Arize account and ax CLI configured locally; agent capabilities limited to what Arize APIs expose. No offline support.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.