The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as node render.mjs and custom tools like video-intake to manage and render the video project.
[DYNAMIC_EXECUTION]: The agent is prompted to dynamically modify a video.js script based on user-defined beat sheets, which is a necessary step for the skill's video automation functionality.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data in the form of transcripts and media assets. 1. Ingestion points: Transcripts and assets provided in Step 1. 2. Boundary markers: None specified. 3. Capability inventory: Execution of scripts and file system operations. 4. Sanitization: No explicit sanitization or validation of input content is mentioned.

explainer-video