The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform all operations, including authentication, creating connections, and executing API actions. This is the intended delivery mechanism for this integration.- [EXTERNAL_DOWNLOADS]: The instructions specify the installation of the @membranehq/cli package via npm. This is a vendor-provided tool required for the skill to function and does not originate from an untrusted source.- [CREDENTIALS_UNSAFE]: The skill explicitly avoids asking for or storing user credentials locally, directing the agent to use the membrane connect workflow which handles tokens securely on the vendor's backend.

enormail