watch

Extract frames and transcribe audio from video content at specified intervals.

6|1|Updated May 29, 2026
One-click install
npx skills add https://github.com/gooseworks-ai/gooseworks-ads-skills --skill watch-gooseworks-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: watch
Source: https://github.com/gooseworks-ai/gooseworks-ads-skills/tree/main/skills/atoms/review/watch
Command: npx skills add https://github.com/gooseworks-ai/gooseworks-ads-skills --skill watch-gooseworks-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, ffprobe, yt-dlp, whisper, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a detailed analysis of video content, enabling users to understand the visual and audio elements present in a rendered video.

Core Features & Use Cases

  • Video Content Analysis: Offers a comprehensive observation report of video content, including visuals, voiceover, music, and sound effects.
  • Timestamped Reporting: Generates a timestamp-keyed observation report for precise analysis.
  • Customization: Allows users to specify video ranges, frame rates, and audio inclusion options.
  • Use Case: Ideal for reviewing ads or videos before production, where understanding the content in detail is crucial.

Quick Start

Analyze the video content of 'ad.mp4' with all audio tracks included and focus on the end card.

Frequently Asked Questions about watch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio and extract frames for video content analysis?

Video content analysis extracts frames and transcribes audio at specified intervals, generating a timestamp-keyed observation report. It processes visuals, voiceovers, music, and sound effects for detailed review.

Do I need ffmpeg and Whisper to run video observation and transcription workflows?

Yes, video observation workflows require ffmpeg, ffprobe, yt-dlp, and Whisper. These dependencies handle video processing, metadata extraction, downloading, and audio transcription respectively.

Can I analyze specific video ranges and customize frame rates during video review?

Yes, video review allows you to specify custom video ranges, frame rates, and audio inclusion options. This targets specific sections like end cards while outputting detailed observation reports and frame samples.

What is the best way to review ad videos before production using automated transcription?

Automated transcription and frame extraction provide a timestamp-keyed observation report for ad videos. This details visuals, voiceover, music, and sound effects, making pre-production video review precise.

Does yt-dlp work with ffmpeg for downloading and analyzing video content?

Yes, yt-dlp downloads video content which ffmpeg and ffprobe then process for frame extraction and metadata. Whisper simultaneously transcribes the extracted audio to generate a comprehensive observation report.