The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the Membrane CLI (@membranehq/cli) via the npm registry. This is an official tool provided by the vendor to facilitate the integration.
[COMMAND_EXECUTION]: The skill uses the membrane command-line interface to perform administrative tasks such as logging in, creating service connections, and executing API actions. These commands are part of the intended workflow for interacting with the platform.
[CREDENTIALS_UNSAFE]: The skill explicitly instructs the agent to avoid asking for API keys or tokens, leveraging the platform's connection management system instead, which is a significant security best practice.
[DATA_EXFILTRATION]: No unauthorized data transfer or exfiltration patterns were identified. Data movement is restricted to the Benchmark Email service through the authenticated Membrane connection.

benchmark-email