The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the ax CLI (e.g., ax experiments list, ax experiments export, ax profiles show) to interact with the Arize platform. These commands are necessary for the skill's primary function and are documented with clear usage instructions.
[EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the arize-ax-cli and various AI provider SDKs (openai, anthropic, google-genai) using standard package managers like pip, pipx, or uv. These are well-known, official packages from trusted sources.
[CREDENTIALS_SAFE]: The skill includes explicit security guidelines preventing the agent from reading .env files or searching for secrets in the filesystem. It correctly instructs users to set environment variables like ARIZE_API_KEY in their own shell and references them via variables (e.g., --api-key $ARIZE_API_KEY) rather than hardcoding values or asking the user to paste them into chat.

arize-experiment