The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the arize-ax-cli (ax) command-line tool to interact with the Arize platform. It performs operations such as exporting telemetry spans, creating judge definitions, and triggering evaluation runs.
[EXTERNAL_DOWNLOADS]: The documentation in references/ax-setup.md provides instructions for installing the arize-ax-cli package using standard package managers like pip, uv, or pipx. These are downloads from a well-known service provider.
[PROMPT_INJECTION]: The skill contains a potential surface for indirect prompt injection.
Ingestion points: Data is ingested via ax spans export and ax experiments export commands (SKILL.md).
Boundary markers: There are no explicit boundary markers or instruction-ignoring delimiters used when displaying exported data in the agent's context.
Capability inventory: The skill has capabilities to execute ax CLI commands for data export, resource creation, and integration management across multiple files (SKILL.md, references/ax-profiles.md).
Sanitization: There is no evidence of sanitization or filtering of the telemetry data before it is read by the agent for structural analysis.

arize-evaluator