The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli global package via npm. This is the official command-line interface provided by the developer (membranedev) to facilitate secure integrations and is a standard requirement for using the platform.
[COMMAND_EXECUTION]: The documentation includes several examples of executing membrane CLI commands to manage connections and run actions. These commands are restricted to the functionality of the integration and do not involve arbitrary or dangerous system commands.
[SAFE]: The skill explicitly advises against manual credential handling, instead directing users to use an OAuth-based connection flow managed by the Membrane platform. This approach significantly reduces the risk of credential leakage or exposure within the agent's context.

ataccama