The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the user to register the Buzzmark MCP server using the claude mcp add command.
[EXTERNAL_DOWNLOADS]: The skill connects to the remote MCP server located at https://buzzmark.ai/mcp. This is a vendor-owned resource necessary for the skill's primary functionality.
[CREDENTIALS_UNSAFE]: The skill instructs users to manage their authentication using the BUZZMARK_API_KEY environment variable. This is a recommended practice for secure secret management in AI agent environments.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external data sources such as news feeds and existing social media posts to generate content.
Ingestion points: External news content via get_post_ideas and existing post content via list_posts.
Boundary markers: No explicit boundary markers or delimiters for remote content are specified in the instructions.
Capability inventory: The skill has the ability to write, schedule, and manage social media drafts.
Sanitization: No specific sanitization methods for retrieved data are described in the instructions.

buzzmark