---

name: video-analysis description: "AI-powered video understanding and analysis toolkit. Use this skill when Claude needs to: (1) Analyze video files (.mp4, .mov, .avi, .mkv, .webm, screen recordings), (2) Extract video content or summarize videos, (3) Identify key moments with timestamps, (4) Analyze product demos or app tutorials, (5) Transcribe or understand video content, (6) Extract frames or screenshots from video, or any other video understanding task. Supports: general video summary, product feature extraction, key moment identification with timestamps, and custom prompt-based analysis."

Video Analysis

AI-powered video content understanding capability that enables intelligent analysis of video files.

Prerequisites

• Python 3.7+
• ARK_API_KEY environment variable (Volces ARK API required)
• Required packages: openai (Volces ARK API is compatible with OpenAI SDK)

Note: This skill uses Volces (火山引擎) ARK API for video analysis. The API is OpenAI-compatible, so we use the OpenAI SDK with a custom base URL.

Quick Start

Copy# Set up API key
export ARK_API_KEY="your_api_key_here"

# Run analysis
python -c "
from scripts.video_analyzer import VideoAnalyzer
result = VideoAnalyzer().analyze_video('demo.mp4', 'general')
print(result['analysis_result']['summary'])
"

Common Use Cases

Analysis Types

See Analysis Types for detailed usage of each type.

Complete Workflow Example

Copyfrom scripts.video_analyzer import VideoAnalyzer

# Initialize analyzer
analyzer = VideoAnalyzer()

# Example 1: Get video summary
result = analyzer.analyze_video("demo.mp4", "general")
print(result['analysis_result']['summary'])

# Example 2: Extract product features
result = analyzer.analyze_video("app_demo.mp4", "product")
print(f"Product: {result['analysis_result']['product_name']}")
print(f"Features: {result['analysis_result']['key_features']}")

# Example 3: Get key moments for testing
result = analyzer.analyze_video("tutorial.mp4", "key_nodes")
for node in result['analysis_result']['key_nodes']:
    print(f"[{node['timestamp']}] {node['description']}")

See API Reference for complete documentation.

Output Format

All results return structured JSON with analysis_result and metadata.

See Output Guide for quality standards and examples.

Error Handling

Handle common errors: FileNotFoundError, ValueError, RuntimeError.

See Error Handling for detailed troubleshooting.

Configuration

Set environment variable:

Copy# Option 1: Temporary (current session only)
export ARK_API_KEY="your_api_key_here"

# Option 2: Permanent (add to ~/.zshrc)
echo 'export ARK_API_KEY="your_api_key_here"' >> ~/.zshrc
source ~/.zshrc

# Verify it's set
echo $ARK_API_KEY

Optional: Override in VideoAnalyzer constructor with api_key, base_url, or model parameters.