Video frame extraction
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
npx -y skills add cxcscmu/SkillLearnBench --skill video-frame-extractionAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Use this skill to extract key frames from MP4 video files into a target directory.
SKILL.md
0.5 KB, as published. Nobody here has run it
Video Frame Extraction
Use FFmpeg to extract key frames from video files.
Usage
Run the following command in the terminal to extract frames:
ffmpeg -i <input_video.mp4> -vf "select='eq(pict_type,PICT_TYPE_I)'" -vsync vfr /root/keyframes_%03d.png
Parameters
<input_video.mp4>: Path to the input video file./root/keyframes_%03d.png: Target file pattern for extracted frames.