The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process local files (experiments/summary.md and yolo-project.yaml) to identify models and class definitions for deployment.
Ingestion points: Reads experimental summaries and project configuration files from the local file system (SKILL.md).
Boundary markers: None present.
Capability inventory: Can execute local deployment tools (yolo-cvat, nuctl) and read/write files within the serverless/ subdirectory.
Sanitization: No explicit sanitization or validation of the contents of these files is described.
[COMMAND_EXECUTION]: The skill utilizes command-line interfaces to perform model conversion and deployment tasks.
Evidence: Generates and suggests execution of yolo-cvat deploy and nuctl deploy commands to manage serverless functions on the local platform.

cvat-deploy