The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package via NPM to facilitate communication with the CRM. This is a vendor-owned package associated with the integration platform.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to execute API actions and proxy requests to SuperOffice. This is the intended behavior for interacting with the CRM.
[PROMPT_INJECTION]: The skill processes external data from SuperOffice (e.g., support tickets, notes), which presents an inherent surface for indirect prompt injection. This is a common characteristic of CRM integrations.
Ingestion points: CRM data retrieved via list-tickets, list-appointments, and direct membrane request calls.
Boundary markers: No specific delimiters or instructions to ignore embedded content are explicitly defined in the skill documentation.
Capability inventory: The skill can create, update, and delete CRM entities (e.g., create-ticket, update-contact) via the membrane action run command.
Sanitization: The skill relies on the LLM's internal safety guardrails and the structured schemas provided by the Membrane platform to handle retrieved data.
[CREDENTIALS_UNSAFE]: The skill correctly delegates authentication to the Membrane platform, avoiding the need to handle or store API keys locally.

superoffice