The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Membrane CLI to interact with the platform for Ngrok management.
Commands such as membrane login, membrane connect, and membrane action run are used to manage the lifecycle of tunnels and integrations.
[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the public NPM registry.
This is the official tool provided by the vendor (Membrane) to interface with their service and is an expected dependency for the skill's functionality.
[PROMPT_INJECTION]: The skill provides an interface for dynamic action discovery and creation which ingests untrusted data.
Ingestion points: User-provided strings are used in membrane action list --intent "QUERY" and membrane action create "DESCRIPTION" (SKILL.md).
Boundary markers: Commands do not use specific delimiters for the natural language parameters.
Capability inventory: The skill can execute actions against the Ngrok API via the Membrane platform using membrane action run (SKILL.md).
Sanitization: The skill relies on the Membrane platform's internal logic to safely interpret and generate actions from user descriptions.

ngrok