The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for users to connect the Clueso Model Context Protocol (MCP) using CLI commands such as claude mcp add. These commands target the vendor's official domain (clueso.io) and are standard for configuring the required tool connection.
[EXTERNAL_DOWNLOADS]: The skill references documentation and connection endpoints hosted on clueso.io. These are trusted resources belonging to the skill author and are necessary for the skill's intended functionality.
[PROMPT_INJECTION]: The skill processes untrusted input in the form of pasted text or uploaded files to generate scripts. While this constitutes an indirect prompt injection surface, the risk is minimal as the agent's actions are focused on content distillation and media generation.
Ingestion points: SKILL.md (Pasted text, Clueso workspace articles, and local files).
Boundary markers: Absent; the skill does not explicitly use delimiters to wrap the ingested external content.
Capability inventory: The skill uses the clueso-mcp to create projects, upload assets, generate narration, and export videos.
Sanitization: No specific sanitization or validation of the input text is described in the workflow.

article-to-video