Skip to main content
Arize Skills encode the workflows we’ve refined building the Arize AX platform and helping teams debug LLM apps in production. They handle the ax CLI flags, data shape quirks, and multi-step recipes so your agent doesn’t have to guess. Your agent gets the full Arize workflow — add tracing, export traces, create datasets, run experiments, set up evaluators, manage annotations, optimize prompts — all through natural language.

Next steps

Install & authenticate

Install the AX CLI, set up credentials, and add skills to your agent.

Skill catalog

Every available skill and what it does.

CLI reference

Flags for ax skills install and ax skills clear.

Coding agent setup

The other agent paths — npx evals or ax instrument, Paste-and-Go, and MCP servers.

Skills, MCP servers, or one-command setup?

  • Skills — you want your agent to run Arize workflows end to end: export traces, build datasets, run experiments, create evaluators, optimize prompts.
  • MCP servers — you want persistent instrumentation guidance and doc search in your IDE.
  • The AX MCP server — you want your agent to work with what is already in Arize: projects, traces, datasets, experiments, prompts. It can read and write, and it is currently in alpha.
  • npx evals or ax instrument — you have no account or traces yet and want one command to do everything.
Looking for the skills you attach to an Arize managed agent? Those are a different thing — account-level integrations managed from Space Settings that let an Arize-hosted worker reach GitHub, Dynatrace, Datadog, the Arize API, or a custom GitHub-hosted skill. Same idea, different runtime: those run in Arize, these run on your machine.