A multimodal tool that analyzes video frames and audio to generate comprehensive, structured Chinese reports.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install universal-video-analyzer-zh
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 universal-video-analyzer-zh 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 Universal Video Analyzer (Chinese)?
The Universal Video Analyzer (Chinese) is a professional-grade tool designed for deep video interpretation using advanced multimodal LLMs. It combines visual keyframe analysis with Whisper-based speech-to-text transcription to provide a dual-track understanding of video content. By leveraging this tool within Openclaw Skills, developers and researchers can transform raw video files into highly organized insights, covering visual scene descriptions and complete audio transcripts, all delivered in formatted Chinese reports.
Universal Video Analyzer (Chinese) Use Cases
- Automated video summarization and scene-by-scene highlights for content creators.
- Transcribing and analyzing recorded meetings, webinars, or interviews.
- Content auditing for digital marketing and social media platforms.
- Educational video processing to create searchable text indices and study notes.
- Rapid review of surveillance or security footage through visual recognition.
How Universal Video Analyzer (Chinese) Works
- The user provides a video file path (e.g., .mp4, .mov) as an input to the skill.
- FFmpeg is utilized to extract representative keyframes from the video track.
- OpenAI Whisper processes the audio stream to generate an accurate text transcript.
- Keyframes (base64 encoded) and the transcript are sent to the configured multimodal LLM API.
- The AI synthesizes visual and auditory data to generate structured Markdown and HTML reports saved locally.
Universal Video Analyzer (Chinese) Setup
Install the required Python dependencies:
pip install requests openai-whisper torch tenacity Pillow python-dotenv
Ensure FFmpeg is installed on your system:
- macOS:
brew install ffmpeg - Windows:
winget install Gyan.FFmpeg - Linux:
sudo apt install ffmpeg
Set the mandatory environment variable for the model provider:
export VIDEO_ANALYZER_API_KEY="your_multimodal_api_key"
You can optionally configure VIDEO_ANALYZER_MODEL and VIDEO_ANALYZER_BASE_URL to use Doubao, Zhipu GLM, or Qwen VL.
Universal Video Analyzer (Chinese) Data Schema & Taxonomy
The skill organizes its output locally to ensure privacy and accessibility:
| Output Type | Format | Description |
|---|---|---|
| Markdown Report | {VideoName}_分析报告.md |
Structured text report including core highlights and scenes. |
| HTML Report | {VideoName}_分析报告.html |
Visual report with embedded keyframes and formatted transcription. |
| Keyframe Folder | {VideoName}_frames/ |
Directory containing all individual images extracted from the video. |
Universal Video Analyzer (Chinese) Advanced Features
- Dual-track analysis providing a holistic view of both visual and audio data.
- Model-agnostic compatibility with major Chinese LLM providers like Doubao, Zhipu GLM-4V, and Qwen-VL.
- Automatic generation of visual HTML reports for professional presentations.
- Localized data processing ensuring that video analysis results remain on your machine.
- Intelligent error handling and cross-platform path compatibility for seamless Openclaw Skills integration.
SKILL.md
Loading
Related Openclaw Skills
Steve Jobs Perspective
A strategic advisor skill that applies Steve Jobs' core decision-making lenses to product design, focus, and end-to-end user experiences.
HeyGen AI
A professional AI video generation skill that converts text scripts and images into high-quality talking avatar presenter videos using cloud-based GPU rendering.
Photo Video Maker Fast
Transform your image collections into polished 1080p videos in under a minute using cloud-accelerated AI.
Video Generation AI Tools
An AI-powered skill for generating professional 1080p videos from text descriptions and image assets using cloud-based GPU rendering.
Web Content Extractor
A sophisticated utility designed to scrape and convert unstructured webpage data into clean, structured JSON format.
AI Aging OpenAPI Skill
An AI-powered age progression tool that transforms portraits to visualize how individuals will look as they grow older.
Featured*
