Skills/
Only outputs with a direct recorded relationship appear below.
Generated outputs that directly record this skill or its named repository.
Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or local WhisperX / cloud Whisper fallback), and hands the result to the agent so it can answer questions about what's in the video. With a Gemini API key, Google's agentic video model watches the full video instead.
Only outputs with a direct recorded relationship appear below.Generated outputs that directly record this skill or its named repository.
Outputs that record this skill will appear here without being inferred from installs or mentions.