The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run grep on the local project files to detect imports from machine learning and GenAI libraries, which helps in categorizing the use case.
[COMMAND_EXECUTION]: It uses the mlflow CLI and jq to query experiment details and verify successful integration by checking for the existence of traces or training runs.
[SAFE]: The use of shell commands and temporary files in /tmp/ is restricted to project discovery and verification. These actions are transparently documented and align with the skill's primary onboarding function without involving remote execution or data exfiltration.

mlflow-onboarding