YouTube Watcher for Openclaw

A specialized skill to fetch, read, and analyze YouTube video transcripts for summarization and information extraction.

naliehu
v1.0.0
Feb 10, 2026
0
1.8k
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install youtube-watcherkx

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-watcherkx 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 technical utility designed to bridge the gap between video content and textual analysis. By leveraging the yt-dlp library, this skill allows users to pull closed captions or auto-generated subtitles directly into their workspace. It is one of the essential Openclaw Skills for developers and researchers who need to process video data without manually watching hours of footage.

This skill integrates seamlessly into automated workflows, enabling rapid parsing of video content for insights, documentation, or study. It serves as a bridge for AI agents to 'see' the textual content of videos, making it an invaluable tool for information synthesis and content research.

YouTube Watcher Use Cases

  • Summarizing long-form educational videos or tutorials to save time.
  • Extracting specific technical information or code snippets mentioned in a video.
  • Answering questions based on the content of a recorded webinar or keynote.
  • Fact-checking video content against textual sources by searching the transcript for keywords.

How YouTube Watcher Works

  1. The user provides a YouTube URL through a trigger command like 'summarize video'.
  2. The skill invokes a Python script that utilizes the yt-dlp backend to interface with YouTube.
  3. The system scans the video metadata to locate available closed captions or auto-generated subtitles.
  4. Transcript data is retrieved, cleaned, and formatted as a plain text string.
  5. The resulting text is returned to the agent for summarization, analysis, or direct display to the user.

YouTube Watcher Setup

To use this skill, ensure you have the necessary dependencies installed on your system. You can install yt-dlp via Homebrew or pip:

# Install via Homebrew
brew install yt-dlp

# Or install via pip
pip install yt-dlp

The skill executes via a Python script. To manually fetch a transcript, you can run:

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

YouTube Watcher Data Schema & Taxonomy

Data Point Detail
Input Format Valid YouTube URL string
Output Format Raw text transcript of the video
Engine yt-dlp
Supported Tracks Manual CC and Auto-generated subtitles
Metadata Storage Stored within the clawdbot configuration schema

YouTube Watcher Advanced Features

  • Support for multi-language closed captions when available.
  • Integration with auto-generated subtitle tracks for videos without manual captions.
  • Command-line flexibility allowing for direct script invocation outside of the agent UI.
  • Robust error reporting for videos that do not contain any subtitle data.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*