The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official npm registry. This is a standard procedure for using the vendor's provided tooling.
[REMOTE_CODE_EXECUTION]: Uses npx to execute the latest version of the Membrane CLI for action discovery. This is a common and safe pattern for executing trusted vendor utilities without a global install.
[COMMAND_EXECUTION]: Performs shell execution of the membrane command to manage authentication, list connections, and execute database actions. These commands are essential for the skill's primary function and are used within their intended scope.
[CREDENTIALS_UNSAFE]: Follows security best practices by explicitly advising against asking for or hardcoding API keys, instead using an OAuth-based connection system managed by the platform.

redis-labs