watch

watch lets you analyze any video by intelligently sampling frames at scene changes, measuring editorial pacing (cuts per minute, shot length), and applying dense analysis to the critical first 10 seconds. It pulls transcripts from captions or Whisper, generates a structured report, and optionally saves findings to your Obsidian vault.

Video Watch processes video URLs and local files to generate artifacts that GitHub Copilot can analyze, including captions, sampled frames, contact sheets, and a prompt packet. Use it when you need Copilot to inspect, summarize, or diagnose video content like demos, recordings, or tutorials. The skill handles multiple detail modes to balance speed and visual coverage.

Video Clipper transforms long-form content like podcasts and interviews into polished short-form vertical videos optimized for social platforms. It handles transcription, identifies high-engagement moments using a viral-scoring rubric, extracts clips, applies speaker-tracked reframing to 9:16 format, and adds professional animated captions—all in one workflow.

Watch Skill processes videos locally by extracting scene-aware frames, running OCR on text within them, and transcribing audio via offline Whisper or captions. It builds a searchable index so follow-up questions are answered without re-processing the video. No API keys required for core features; vision and STT are optional and configurable.

Watch Skill processes any video—URLs, local files, streams, recordings—by extracting frames, running OCR, and transcribing audio into a unified searchable index. Query the index directly instead of re-watching, and batch-process playlists or folders in one pass.

Master video clipping workflows with detailed reference material for yt-dlp downloads, Whisper transcription with word-level timing, SRT subtitle generation, and ffmpeg video processing. Learn platform-specific shell syntax, model selection, scene and silence detection, vertical video formatting, and caption styling across Windows, macOS, and Linux.