The Agent Skills Directory

[SAFE]: The skill uses the official Membrane CLI (@membranehq/cli) for all operations. This package is maintained by the skill's author (membranedev) and is the primary interface for the service.
[CREDENTIALS_SAFE]: The skill implements secure authentication practices. It specifically instructs the agent to "never ask the user for API keys or tokens" and instead use membrane connect, which handles secrets server-side, reducing the risk of credential exposure in the agent's context.
[COMMAND_EXECUTION]: Shell commands are used to interact with the Membrane CLI. These commands are well-defined and scoped to the integration's purpose, including authentication, action discovery, and execution.
[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official npm registry. This is a standard dependency for the toolset provided by the author and is documented neutrally.

sumo-logic