ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified media Safety 4/5

vidiq

AI-powered video intelligence - download, analyze, clip, GIF from any URL. Supports YouTube, TikTok, Instagram, X. Uses ffmpeg + yt-dlp.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/cassh100k/vidiq
Or

What This Skill Does

The VidIQ skill is a robust video intelligence toolkit designed for OpenClaw agents to perform deep analysis and manipulation of video content from virtually any online source. By leveraging the industry-standard yt-dlp for downloads and ffmpeg for processing, VidIQ allows your agent to bridge the gap between static text-based interactions and rich media content. Whether you need to extract specific frames for visual analysis, convert video segments into GIFs, or isolate audio tracks for transcription, this tool provides a unified command-line interface to perform complex media engineering tasks programmatically.

Installation

To integrate VidIQ into your OpenClaw environment, ensure you have both ffmpeg and yt-dlp installed on your host system. Once prepared, run the following command in your terminal:

clawhub install openclaw/skills/skills/cassh100k/vidiq

This will pull the necessary scripts into your baseDir/scripts/ directory. Ensure your environment has sufficient write permissions to the /tmp/vidiq/ directory, as this is where all caching, frame extraction, and temporary output generation occur.

Use Cases

  • Automated Video Summarization: Extract keyframes from a long tutorial to feed into a vision model to generate a descriptive summary.
  • Content Curation: Create quick, optimized GIFs from long-form social media content for use in documentation or presentations.
  • Media Archiving: Automatically strip audio from video URLs for storage or separate processing workflows.
  • Quality Assurance: Use the mosaic and scene detection features to visually audit large batches of video files for transitions or glitches.

Example Prompts

  1. "Download this YouTube video and extract 20 frames spaced evenly to create a visual storyboard, then describe the content in each frame."
  2. "Find the scene in this TikTok video where the presenter starts speaking about AI and clip that 10-second segment into a new file."
  3. "Create a 5-second GIF starting at the 30-second mark of this Twitter video URL and save it to my local media folder."

Tips & Limitations

  • Caching: The tool caches downloads in /tmp/vidiq/. If you are processing many large files, remember to clear this directory periodically to reclaim disk space.
  • Frame Coverage: For longer videos, the default frame extraction count might miss significant content. Increase the frame count for high-motion or information-dense videos.
  • Performance: Complex video operations like mosaic generation or heavy transcoding can be CPU-intensive; use this skill during off-peak hours for large batches.
  • Platform Compatibility: While it supports major platforms, ensure your yt-dlp is updated frequently, as platforms often change their scraping protocols.

Metadata

Author@cassh100k
Stars4072
Views1
Updated2026-04-13
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-cassh100k-vidiq": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#video#automation#ffmpeg#vision#media
Safety Score: 4/5

Flags: network-access, file-write, file-read, code-execution