The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash(uv:*) tool to execute a local Python script (generate.py) that handles image generation logic. It also provides templates for ffmpeg commands to assist the agent in extracting frames from video files for use as image references.
[EXTERNAL_DOWNLOADS]: The skill communicates with Google's Gemini API endpoints (gemini-3.1-flash-image-preview and gemini-3-pro-image-preview) to perform its primary function. It also supports optional Google Search grounding for both text and images, which involves legitimate external network requests to Google services.

generate-image