The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the @membranehq/cli to interact with the Membrane platform. Commands like membrane login, membrane connect, and membrane action run are utilized to manage the integration lifecycle and execute remote tasks via the vendor's infrastructure. These are expected behaviors for a connector-based skill.
[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the @membranehq/cli package globally via NPM. This package is the official tool provided by the vendor for interacting with their platform.
[CREDENTIALS_UNSAFE]: The skill follows secure authentication practices by delegating credential management to the Membrane platform. It specifically instructs users not to handle API keys or secrets directly, using a browser-based OAuth flow instead.
[SAFE]: No malicious patterns such as data exfiltration, prompt injection, or obfuscation were detected. All external references and tools originate from the verified vendor's official resources.

gobiolink