The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official NPM registry. This is a legitimate utility provided by the skill author (membranedev) to facilitate communication with their platform.
[COMMAND_EXECUTION]: The skill uses shell commands to interact with the membrane CLI for logging in, connecting to services, and running actions. These operations are transparent and necessary for the intended functionality.
[SAFE]: The skill explicitly advises against asking the user for API keys or tokens, directing the agent to use Membrane's connection management system which handles credentials server-side. This reduces the risk of credential exposure.

wobaka