The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill guides the user to install the @membranehq/cli package from the official npm registry. This is a standard procedure for using the vendor's command-line interface to manage integrations.
[COMMAND_EXECUTION]: The skill uses shell commands via the membrane CLI to authenticate users, list connections, and execute actions. These commands are restricted to the functionality provided by the Membrane platform.
[DATA_EXPOSURE]: The skill processes security data from Threat Stack, including alerts and observations. The instructions follow best practices by delegating credential management to the Membrane platform rather than handling secrets locally.
[REMOTE_CODE_EXECUTION]: The membrane action create command allows for the dynamic generation of integration logic based on natural language descriptions. This behavior is a core feature of the Membrane platform for building automated workflows.

threat-stack