Video 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-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 keyframes from video files using FFmpeg. It covers selecting the right extraction frequency and naming conventions for image sequences.
SKILL.md
1.0 KB, as published. Nobody here has run it
Video Extraction Skill
This skill provides instructions for extracting keyframes from video files (e.g., MP4) using ffmpeg.
Prerequisites
ffmpegmust be installed in the environment.
Extraction Commands
To extract keyframes from a video file:
ffmpeg -i input_video.mp4 -vf "select='eq(pict_type,PICT_TYPE_I)'" -vsync vfr output_prefix_%03d.png
-i input_video.mp4: Specifies the input video file.-vf "select='eq(pict_type,PICT_TYPE_I)'": Filters for I-frames (keyframes).-vsync vfr: Variable frame rate, ensures only selected frames are output.output_prefix_%03d.png: The output filename pattern.
Naming Convention
For this task, use the following pattern:
/root/keyframes_%03d.png
Verification
After extraction, list the files in the output directory to confirm they were created.