YouTube Watcher for Openclaw

A specialized tool for extracting text transcripts from YouTube videos to enable AI-powered summarization and content analysis.

stveenli
v1.0.0
Feb 7, 2026
0
0
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install ytwatchervideo

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 ytwatchervideo 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 integration for Openclaw Skills designed to streamline the way AI agents interact with video content. By bridging the gap between multimedia and text, this skill allows users to feed YouTube URLs into their workflow and receive clean, searchable transcripts in return. Whether you are dealing with official closed captions or auto-generated subtitles, this tool ensures your agent has the raw data needed for high-level reasoning.

This skill is built for developers and researchers who need to process large amounts of video data efficiently. By utilizing the reliable yt-dlp engine, it provides a stable interface for fetching content that can then be used for complex tasks like sentiment analysis, tutorial summarization, or deep-dive QA sessions within the ecosystem of Openclaw Skills.

YouTube Watcher Use Cases

  • Summarizing lengthy webinars or technical tutorials into bite-sized bullet points.
  • Searching for specific keywords or mentions within a video transcript without watching the entire file.
  • Generating automated Q&A datasets based on video interviews or educational content.
  • Extracting code snippets or technical instructions mentioned in dev-focused YouTube videos using Openclaw Skills.

How YouTube Watcher Works

  1. The user provides a YouTube URL through a trigger command like "summarize video".
  2. The skill invokes the internal Python script get_transcript.py.
  3. The script utilizes the yt-dlp backend to identify and download available subtitle tracks (manual or auto-generated).
  4. The raw subtitle format is parsed into a clean text stream.
  5. The extracted text is returned to the AI agent to perform requested tasks like summarization or information retrieval.

YouTube Watcher Setup

This skill requires OpenClawCLI to be installed on your system. Additionally, you must have yt-dlp available in your PATH. You can install it using one of the following commands:

# For macOS users via Homebrew
brew install yt-dlp

# For Python environments via Pip
pip install yt-dlp

Ensure that the baseDir in your Openclaw Skills configuration points to the correct local directory where the scripts are hosted.

YouTube Watcher Data Schema & Taxonomy

The skill processes video metadata and subtitle tracks to produce a textual output. The following structure outlines the data handling:

Component Type Description
Input URL String The valid YouTube video link provided to the script.
Transcript String The raw text extracted from the video's subtitle track.
Error Message String Returned if the video has no captions or is private.
Script Path path Located at scripts/get_transcript.py within the skill directory.

YouTube Watcher Advanced Features

  • Multi-platform support for both Windows and MacOS via OpenClawCLI.
  • Fallback mechanism that attempts to fetch auto-generated subtitles if manual captions are unavailable.
  • Seamless integration with other Openclaw Skills for multi-agent research workflows.
  • CLI-first architecture allowing for easy integration into custom shell scripts or automated pipelines.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*