The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard development tools including the databricks CLI, uv, and curl. These are used for administrative tasks such as resource validation, deployment, logging, and application querying which are core to the skill's stated purpose.- [CREDENTIALS_UNSAFE]: The skill handles authentication by guiding the user to retrieve OAuth tokens via the CLI. It uses safe placeholders for sensitive values and recommends using .env files for configuration, following industry standard practices for secret management.- [INDIRECT_PROMPT_INJECTION]: The skill involves reading and processing output from CLI commands (e.g., JSON output from databricks apps get) and network responses. While this constitutes an external data ingestion surface, it is necessary for the deployment logic and does not introduce unusual risk beyond the inherent behavior of a deployment tool.

deploy