A professional-grade tool for native video analysis, summarization, and metadata extraction using the Google Gemini API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install a6-gemini-video-analyzer
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 a6-gemini-video-analyzer 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 Gemini Video Analyzer?
The Gemini Video Analyzer is a sophisticated integration designed to leverage Google's multimodal capabilities for deep video understanding. By utilizing the Openclaw Skills framework, this tool enables developers to skip the tedious process of manual frame extraction. Instead, it processes video natively at 1 frame per second, allowing the AI to maintain a temporal grasp of motion, transitions, and audio cues.
Whether you are processing screen recordings for bug reports or summarizing long-form tutorials, this skill provides a robust interface to the Google Gemini API. It handles large files up to 2GB and ensures privacy by relying on temporary file storage that auto-expires, making it a reliable choice for automated video research and data extraction.
Gemini Video Analyzer Use Cases
- Summarizing complex video tutorials or meeting recordings into actionable text summaries
- Identifying UI elements and extracting visible text from software demos and walkthroughs
- Analyzing user-submitted screen recordings to identify software bugs and reproduction steps
- Comparing two or more videos to find visual differences, content updates, or branding changes
- Generating automated closed captions or action descriptions to improve content accessibility
How Gemini Video Analyzer Works
- The system uploads the targeted video file to the Google Files API using the included Python management scripts.
- Google Gemini analyzes the video at a rate of 1 frame per second, integrating visual, motion, and audio data for full context.
- The skill sends a specific prompt or a default summary request to the model for intelligent interpretation.
- Gemini returns a detailed analysis based on the video's temporal context and specific user queries.
- Integrated file management tools allow for the tracking and manual cleanup of uploaded assets stored in the cloud.
Gemini Video Analyzer Setup
To begin using these Openclaw Skills, ensure you have a valid API key from Google AI Studio.
# Set your environment variable for authentication
export GOOGLE_AI_API_KEY='your_api_key_here'
# Run the analysis script on a local video file with a default prompt
python3 scripts/analyze.py ./my_video.mp4
# Perform a custom analysis focused on extracting UI components
python3 scripts/analyze.py ./demo.mp4 "What text and UI elements are visible?"
Gemini Video Analyzer Data Schema & Taxonomy
| Feature | Specification |
|---|---|
| Supported Formats | MP4, AVI, MOV, MKV, WebM, FLV, MPEG, MPG, WMV, 3GP |
| Max File Size | Up to 2GB per file |
| Default Model | gemini-2.5-flash |
| Temporal Resolution | 1 Frame Per Second (FPS) with audio context |
| File Retention | 48-hour automatic deletion via Google Files API |
Gemini Video Analyzer Advanced Features
- Support for high-tier models like gemini-2.5-pro for highly complex visual reasoning tasks
- Automated file lifecycle management including list and cleanup commands to manage storage usage
- Native multimodal processing that understands motion and transitions without manual frame splitting
- Flexible CLI parameters to override models and customize analysis depth for various video lengths
SKILL.md
Loading
Related Openclaw Skills
MarketPulse
A comprehensive financial intelligence skill for querying real-time and historical data across equities and cryptocurrencies.
OpenClaw YouTube
A powerful YouTube Search Engine Results Page (SERP) scout designed for autonomous agents to perform deep content and competitor research.
OpenClaw Search
An intelligent multi-source retrieval engine that provides autonomous agents with confidence-scored answers from web and academic sources.
OpenClaw Media Gen
A unified media generation skill for creating high-fidelity images and cinematic videos through the AIsa API.
GitHub Intelligence
A specialized tool for AI agents to analyze GitHub repositories, generate architecture diagrams, and convert codebases into AI-readable markdown documents.
OpenClaw Architect
A comprehensive management and optimization tool for designing, debugging, and maintaining high-performance OpenClaw deployments.
Featured*
