video-watching

Community

Turn videos into time-stamped transcripts.

Authormeanllbrl
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill turns video content into a time-stamped transcript with inline descriptions of on-screen visuals, enabling AI agents and humans to reason about videos without watching every frame.

Core Features & Use Cases

  • Time-stamped transcript and associated frame index (frames.json) that align speech with video timeline.
  • On-screen visuals described inline at relevant timestamps, plus optional anchor frames for opening and closing hooks.
  • Outputs are stored next to the source video (transcript, frames, and a frames.json index) and support modes for marketing, onboarding, and knowledge capture.

Quick Start

Provide a video path or URL and request a time-stamped transcript with inline visual descriptions.

Dependency Matrix

Required Modules

ffmpegffprobeyt-dlpwhisper-cliwhisper-cpppython3

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: video-watching
Download link: https://github.com/meanllbrl/dreamcontext/archive/main.zip#video-watching

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.