The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the NPM registry. This is the official command-line tool provided by the skill author for platform integration.
[COMMAND_EXECUTION]: The skill executes various commands using the membrane CLI to handle authentication, manage service connections, and run actions.
[PROMPT_INJECTION]: The skill processes data from the Membrane API, representing a potential surface for indirect instructions. Ingestion points: Data from membrane action list and membrane action run (found in SKILL.md). Boundary markers: Absent. Capability inventory: Execution of membrane CLI commands (found in SKILL.md). Sanitization: No explicit sanitization of external data is performed before processing.

blockstack