A specialized utility for decomposing video files into individual frames to enable deep visual analysis and scene description.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-watcher
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 video-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 Video Analyzer?
The Video Analyzer is a robust technical tool designed to facilitate the understanding of video content by extracting high-quality frames at regular intervals. It serves as a bridge for AI agents that need to interpret visual data within video files but cannot play them in real-time. By utilizing ffmpeg, this skill supports a wide range of formats including MP4, MOV, AVI, and MKV, making it a versatile addition to any Openclaw Skills library.
Whether you are reviewing technical screencasts, analyzing scene transitions, or extracting UI elements from a recording, this skill provides the necessary visual context. It automates the extraction process and organizes frames logically, allowing developers and agents to build a comprehensive understanding of the video's progression and content through static image analysis.
Video Analyzer Use Cases
- Performing detailed scene analysis on long-form video recordings.
- Identifying specific UI changes or bugs in software walkthrough videos.
- Extracting text or titles from video content for indexing purposes.
- Creating image-based summaries of media files for faster review.
- Documenting visual transitions in video production workflows.
How Video Analyzer Works
- The user provides a path to a video file and specifies an optional output directory and frame rate.
- The skill invokes a bash script that leverages ffmpeg to process the video container.
- Image frames are extracted at the designated frequency (defaulting to 1 frame per second) and saved as JPEGs.
- Metadata such as resolution and duration is captured and displayed during the process.
- The AI agent or user reviews the resulting images to describe or analyze the video timeline.
Video Analyzer Setup
Ensure that ffmpeg is installed on your local environment before using this skill.
# Ubuntu/Debian
sudo apt-get install -y ffmpeg
# macOS
brew install ffmpeg
Once installed, you can extract frames using the following command structure within your Openclaw Skills environment:
scripts/extract_frames.sh <video_path> [output_dir] [fps]
Video Analyzer Data Schema & Taxonomy
The skill organizes its output into a designated directory to maintain a clean workspace for Openclaw Skills workflows.
| Data Point | Type | Description |
|---|---|---|
frame_XXX.jpg |
Image | Individual extracted frames numbered sequentially. |
output_dir |
Directory | A folder containing all frames, defaults to frames_<video_name>. |
metadata |
Text | Console output detailing video duration, resolution, and total frames. |
Video Analyzer Advanced Features
- Variable FPS Extraction: Customize the granularity of analysis by adjusting the frames-per-second parameter.
- High Compatibility: Seamlessly processes various video containers like MKV and AVI using industry-standard ffmpeg.
- Scalable Sampling: Optimized strategies for different video lengths, from 1-second interval reviews for short clips to scene-change focus for long-form content.
- Automated Directory Management: Automatically creates and organizes output folders based on the source filename.
SKILL.md
Loading
Related Openclaw Skills
Bitget Wallet Skill
A powerful crypto utility enabling AI agents to fetch market data, perform security audits, and execute cross-chain swaps with gasless capabilities.
Bitget Wallet Skill
A comprehensive AI agent skill providing deep integration with the Bitget Wallet API for market analysis, token security auditing, and cross-chain swap execution.
OpenClaw Documentation Search & Config Patterns
A specialized documentation search and configuration guardrail system designed to prevent errors when modifying OpenClaw agent settings.
MarkItDown Document Converter
A versatile document conversion engine for transforming various file formats into clean, structured Markdown.
n8n Workflow Builder
A programmatic interface for designing, deploying, and managing n8n automation workflows using a specialized API-driven agent.
Web Searcher
An autonomous research agent that executes multi-angle searches, extracts deep-page content, and synthesizes data into structured, cited reports.
Featured*
