The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Recommends installing the @membranehq/cli tool from the npm registry. This is the official CLI for the platform referenced in the skill metadata and homepage, developed by the vendor.
[COMMAND_EXECUTION]: Uses the membrane CLI to perform authentication, manage LinkedIn connections, and execute actions.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from LinkedIn, creating a surface for potential indirect instructions from external profiles or posts.
Ingestion points: Fetches external content via actions like list-posts, list-comments, and get-post described in SKILL.md.
Boundary markers: None explicitly mentioned in the skill instructions to delimit external content for the agent.
Capability inventory: The skill can modify external state through actions like create-post and delete-post via the membrane action run command in SKILL.md.
Sanitization: No specific sanitization or filtering logic is mentioned for processing data fetched from the API.

linkedin