An AI-driven video intelligence tool for downloading, analyzing, and manipulating media from social platforms using ffmpeg and yt-dlp.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install vidiq
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 vidiq 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 VidIQ?
VidIQ is a robust video processing skill designed to bridge the gap between web-hosted video content and AI vision models. By leveraging powerful backend tools like ffmpeg and yt-dlp, it allows users to programmatically interact with videos from platforms like YouTube, TikTok, Instagram, and X. This skill is a core part of the Openclaw Skills ecosystem, enabling developers to automate video data extraction for deep content understanding and media generation.
Whether you are building a video summarization agent or a social media automation bot, VidIQ provides the necessary primitives to handle high-level media tasks. It simplifies complex video operations—such as scene detection and visual mosaic creation—into straightforward CLI commands that any AI agent can execute within a larger workflow.
VidIQ Use Cases
- Analyzing YouTube or TikTok content via AI vision models for automated summarization.
- Generating high-quality GIFs or clips from social media URLs for digital marketing.
- Automating audio extraction from video sources for transcription or podcasting workflows.
- Performing scene change detection to identify key transitions and chapters in long-form media.
- Creating visual mosaics for quick multi-frame previewing of video files without manual scrubbing.
How VidIQ Works
- The user or agent provides a URL from a supported platform or a local file path to the vidiq script.
- The skill utilizes yt-dlp to fetch the media and caches it locally in a temporary directory to optimize performance for subsequent commands.
- Ffmpeg executes the specific operation requested, such as extracting frames at even intervals or clipping segments based on timestamps.
- Processed data (frames, audio, or clips) is stored in organized subdirectories for easy access by other tools.
- In an AI analysis workflow, the extracted frames are typically passed to a vision model to interpret the visual content and answer complex natural language queries about the video.
VidIQ Setup
To use this skill, ensure that your environment has the required binaries installed. VidIQ depends on ffmpeg for processing and yt-dlp for media acquisition.
# Install dependencies (macOS example)
brew install ffmpeg yt-dlp
# Basic usage to get video information
{baseDir}/scripts/vidiq.sh <url_or_path> info
VidIQ Data Schema & Taxonomy
VidIQ organizes its output within a structured temporary directory to ensure data is easily accessible for downstream Openclaw Skills or vision models.
| Data Type | Location / Format | Description |
|---|---|---|
| Raw Video Cache | /tmp/vidiq/ |
Stores downloaded source files for reuse across different commands. |
| Extracted Frames | /tmp/vidiq/frames_*/ |
Directories containing sequential JPEG/PNG frames. |
| Technical Metadata | CLI Standard Out | Detailed info including duration, resolution, and codecs. |
| Processed Media | .mp4, .mp3, .gif |
Final output files for clips, audio extractions, and animations. |
VidIQ Advanced Features
- Intelligent scene change detection with adjustable sensitivity thresholds for pinpointing edits.
- Palette-optimized GIF generation ensuring high visual quality with minimal file size overhead.
- Visual mosaic generation capable of rendering multi-column previews of entire videos in a single image.
- Cross-platform compatibility covering major social media sites and direct video links.
- Seamless integration hooks for feeding visual data into multi-modal AI agents.
SKILL.md
Loading
Related Openclaw Skills
SoulKeeper
SoulKeeper provides identity persistence for AI agents by auditing core rule files, detecting behavioral drift, and injecting context-aware reminders.
Polymarket Whale Copier
An automated trading tool designed to track and replicate the positions of high-performing Polymarket wallets in real-time.
Memory Guard
Secure your agent's identity and memory files against injection attacks and unauthorized personality drift.
Image Nuke
A high-intensity image anonymization tool that strips all metadata and injects noise to defeat forensic tracking and reverse image search.
xAI Grok Search
A high-performance AI skill leveraging xAI's Grok API to provide real-time web access, X (Twitter) insights, and multi-modal media understanding.
NoChat Channel
A post-quantum end-to-end encrypted messaging channel that enables secure agent-to-agent communication within Openclaw Skills.
Featured*
