Watch

Analyze an existing video from timestamped speech and locally inspected visual evidence. Answer the user's question first; preserve structured concept analysis for general summaries. A transcript explains what was said, not everything shown. Watch processes media locally and does not upload video or audio to a media-analysis service.

When to Use

Request	Evidence mode	Boundary
Summarize spoken ideas, an interview, or a podcast	`transcript`	No video download when captions suffice
Inspect a slide, code, UI demo, or private recording	`local`	Read bounded frames and available speech evidence
Search a long public video for a visual moment	`local`	Start with bounded sampling, then inspect focused intervals; coverage is not exhaustive
Recreate a visual reference	`local`	Pass inspected evidence to a generation skill; Watch does not generate video
Align supplied retention analytics with content	Focused `local`	Association is not proof of why viewers left

Do not activate for video discovery, new-video creation (including HTML/Hyperframes, Manim, or Remotion video), financial watchlists, or watching filesystem changes. Other URL sources use yt-dlp support, not a promise that every website or private video is accessible.

Prerequisites

SKILL_DIR is the absolute directory containing this file; scripts sit beside it. Resolve this path from the installed skill, not the current project directory. Python 3.12+ and uv are required. Local media inspection also needs FFmpeg/ffprobe. The documented uv invocation supplies caption/downloader dependencies without changing the user's project.