analyze_video_clip
Extract keyframes from video clips for AI analysis, generating descriptive metadata to identify content before project selection.
Instructions
Extract keyframes from a video clip for analysis. Returns frames as images for Claude to analyze and generate metadata. After Claude provides analysis, saves metadata JSON file next to the video. Use this to understand what's in a clip before selecting it for a project.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| video_path | Yes | Absolute path to the video file | |
| category | No | Category/subject area (e.g., "physics", "math", "generic"). Optional. | |
| keyframe_count | No | Number of keyframes to extract for analysis (default: 4) | |
| metadata | No | Optional: Claude's analysis to save as metadata. If provided, saves JSON file. Should include: description, tags, mood, subject_visible, subject_position, setting |