YouTube Watcher for Openclaw

A specialized utility for extracting YouTube video transcripts to enable AI-powered summarization and information retrieval.

michaelgathara
v1.0.0
Jan 25, 2026
333
53.2k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install youtube-watcher

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install youtube-watcher using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is YouTube Watcher?

YouTube Watcher is a robust tool designed to integrate seamlessly into your Openclaw Skills library. It focuses on solving the challenge of programmatic video content analysis by extracting closed captions and auto-generated subtitles directly from YouTube URLs. This allows your AI agents to effectively read and understand video content without the need for manual transcription.

By leveraging this skill within the Openclaw Skills ecosystem, developers and researchers can automate the ingestion of vast amounts of video data. Whether you are building a research assistant or a content curator, this skill provides the necessary text-based foundation for deep semantic analysis and question-answering tasks based on video media.

YouTube Watcher Use Cases

  • Automatically summarizing long-form technical webinars or educational lectures.
  • Extracting specific data points or answers from product reviews and video tutorials.
  • Building searchable archives of video content for research purposes.
  • Generating structured notes from video-based meetings or presentations.

How YouTube Watcher Works

  1. The user provides a YouTube URL through an Openclaw Skills trigger such as analyze video or summarize video.
  2. The system invokes the get_transcript.py script which utilizes the yt-dlp backend.
  3. The skill identifies and downloads the most accurate transcript available, supporting both manual CC and auto-generated subtitles.
  4. The resulting text is fed back into the Openclaw Skills pipeline for the AI agent to process, summarize, or search.

YouTube Watcher Setup

To get started with this skill in your Openclaw Skills environment, you must ensure yt-dlp is installed on your system.

Install via Homebrew (macOS):

brew install yt-dlp

Install via Pip:

pip install yt-dlp

Once the dependency is met, the skill can be invoked using the following command structure:

python3 scripts/get_transcript.py "https://www.youtube.com/watch?v=VIDEO_ID"

YouTube Watcher Data Schema & Taxonomy

Component Description
Input YouTube Video URL (string)
Output Plain text transcript extracted from the video source
Dependencies Requires yt-dlp binary available in the system PATH
Compatibility Works with any video containing Closed Captions (CC) or auto-generated subtitles

YouTube Watcher Advanced Features

  • Multi-source installation support including brew and pip for flexible Openclaw Skills deployment.
  • Automatic fallback to auto-generated subtitles when manual captions are unavailable.
  • Optimized for high-speed text retrieval, making it suitable for real-time AI agent interactions.
  • Minimal footprint designed for easy integration into larger automation workflows.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*