Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Extract key frames and text content from video files using ffmpeg and Tesseract OCR.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -67% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -52% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -73% | 0% |
Extracts key frames from MP4 videos, runs Tesseract OCR, and generates structured Markdown reports.
In Codex CLI, invoke the skill.
| Parameter | Type | Description | Default | |-----------|------|-------------|---------| | video_path | string | Path to the video file | required | | output_dir | string | Output directory | same as video | | interval | integer | Frame interval in seconds | 30 | | lang | string | OCR language | chi_sim+eng |
Other measured skills in the registry, with their headline benchmark lift.