The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform operations such as logging in, listing connections, and running actions. These are standard operations for the intended integration.
[EXTERNAL_DOWNLOADS]: Installs the official @membranehq/cli tool via NPM. This is a legitimate dependency required for the skill to function and is sourced from a standard registry.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by explicitly instructing the user to avoid hardcoding API keys or secrets, instead relying on the CLI's built-in authentication flow (membrane login).

crisp