The Agent Skills Directory

[SAFE]: The skill follows secure design patterns by delegating authentication and API logic to a specialized platform (Membrane).
[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package, which is a legitimate vendor resource corresponding to the skill author.
[CREDENTIALS_UNSAFE]: The instructions explicitly discourage asking users for secrets, instead using a secure browser-based OAuth-style flow managed by the Membrane CLI.
[COMMAND_EXECUTION]: Shell usage is limited to the official membrane CLI for platform-related tasks such as connection management and action execution.

small-improvements