The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from the official NPM registry to enable platform interaction.
[COMMAND_EXECUTION]: Utilizes the membrane command-line tool to authenticate, connect to external services, and execute data management actions.
[PROMPT_INJECTION]: The skill accepts natural language input for searching and generating actions. Ingestion points: User-provided strings in the --intent and action create parameters within SKILL.md. Boundary markers: No explicit markers are used to isolate user input in the provided examples. Capability inventory: Shell command execution via the membrane binary for service interaction. Sanitization: None specified in the documentation, assuming enforcement by the CLI or backend service.

grab