The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via NPM. This is the official tool provided by the skill's author (membrane) and is necessary for the skill's functionality.
[COMMAND_EXECUTION]: The skill uses various shell commands through the membrane CLI to manage connections and execute actions. These are standard operational commands for the platform.
[CREDENTIALS_UNSAFE]: The skill explicitly follows best practices by instructing the agent to never ask for API keys or tokens, instead using Membrane's built-in connection management which handles authentication server-side.
[REMOTE_CODE_EXECUTION]: While the skill mentions creating actions dynamically based on descriptions, this process is managed by the Membrane platform's backend infrastructure rather than executing untrusted code directly in the agent's environment.

textcortex