The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs and uses the @membranehq/cli package from the npm registry.
Evidence: Instructions include npm install -g @membranehq/cli@latest and npx @membranehq/cli@latest in SKILL.md.
Context: This is the official command-line tool for the Membrane platform, provided by the skill's author.
[COMMAND_EXECUTION]: The skill relies on the membrane command-line utility to perform authenticated operations and query travel data.
Evidence: Commands such as membrane login, membrane connect, and membrane action run are used throughout the instructions.
Context: These operations are the standard method for using the Membrane integration layer and match the skill's stated functionality.
[CREDENTIALS_UNSAFE]: The skill adopts secure secret management practices by delegating authentication to the Membrane platform.
Evidence: The 'Best practices' section explicitly instructs the agent to avoid asking users for API keys or tokens, relying instead on server-side connection management.

amadeus