A comprehensive automation tool for downloading videos, generating AI-powered transcripts, and capturing periodic screenshots for deep content analysis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install videoanalyzer
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install videoanalyzer 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 Video Watcher?
Video Watcher is a technical utility designed to streamline the ingestion and analysis of video content. As a versatile component of the Openclaw Skills library, it integrates yt-dlp, ffmpeg, and OpenAI's Whisper to convert multimedia into structured data. It handles the heavy lifting of media management, allowing users to focus on deriving insights from transcripts and visual frames.
This skill is particularly useful for developers and researchers who need to process large volumes of video content without manual intervention. By leveraging high-performance open-source tools, Video Watcher ensures that audio extraction and subtitle generation are both accurate and efficient, fitting perfectly into modern AI-driven workflows.
Video Watcher Use Cases
- Processing Due Diligence (DD) videos for investment and research analysis.
- Generating structured lecture notes from university or online courses.
- Creating text-based summaries and archives for podcasts.
- Building technical documentation for software tutorials using captured frames.
- Transcribing and indexing meeting recordings for organizational knowledge management.
How Video Watcher Works
- The skill receives a video URL or file path and utilizes yt-dlp to retrieve the media source.
- ffmpeg is invoked to isolate the audio stream and convert it into a high-quality mp3 for processing.
- The Whisper model processes the audio to generate both plain text transcripts and timestamped subtitle files (SRT).
- Simultaneously, ffmpeg captures video screenshots at specified intervals (defaulting to every 30 seconds) to provide visual context.
- All generated assets are saved into a timestamped or named directory for easy access and integration with other Openclaw Skills.
Video Watcher Setup
To utilize Video Watcher, you must first install the required binary dependencies on your system:
brew install yt-dlp ffmpeg openai-whisper
Once installed, you can trigger a full analysis with a single command:
./scripts/analyze.sh "https://youtube.com/watch?v=VIDEO_ID"
Video Watcher Data Schema & Taxonomy
The skill organizes output into a dedicated directory structure for clear data management:
| Asset | Path | Description |
|---|---|---|
| Video File | outputs/video.mp4 |
The raw video download. |
| Audio File | outputs/audio.mp3 |
Extracted audio track. |
| Text Transcript | outputs/transcript.txt |
Clean text version of the speech. |
| Subtitles | outputs/transcript.srt |
Subtitle file with precise timing. |
| Visual Frames | outputs/frames/ |
Folder containing screenshots for visual reference. |
Video Watcher Advanced Features
- Support for multiple Whisper model sizes (base, medium, large) to balance speed and transcription accuracy.
- Configurable frame-capture intervals for more granular or high-level visual summaries.
- Native integration with AI agents for automatic summarization of generated transcripts.
- Flexible output directory configuration to support large-scale media processing pipelines within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Video Watcher
Download videos, transcribe audio with Whisper, and extract frames for deep content analysis.
Arena System
An adversarial self-improvement framework that reduces AI hallucinations through agent versus anti-agent debate loops.
Venus Protocol Ops
A risk-first AI agent skill for analyzing and managing lending positions on the Venus Protocol.
WeChat Moments Copy Critic
A specialized AI tool for analyzing and improving the persuasiveness of WeChat Moments social media copy using a 5-point evaluation framework.
Arena System
The Arena System implements an adversarial self-improvement framework where AI agents engage in debate loops to minimize hallucinations and validate logic.
Video Watcher
An automated utility for downloading videos, generating high-accuracy transcripts with Whisper, and extracting frames for visual analysis.
Featured*
