agentsclimarketplace

Run2 video frame extraction

Skill cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-flash-lite-preview/video-object-counting/run2_video-frame-extraction

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run2_video-frame-extraction

Assembled 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

Extracts all key frames from a video file into a specified output directory using FFmpeg.

SKILL.md

0.8 KB, as published. Nobody here has run it

Overview

This skill extracts keyframes (I-frames) from video files into individual PNG files. This is useful for object detection over time.

Usage

To extract keyframes as PNG files, use the following command:

ffmpeg -i <input_file> -vf "select='eq(pict_type,PICT_TYPE_I)'" -fps_mode vfr -vsync vfr /root/keyframes_%03d.png
  • -i: Input video file.
  • -vf "select='eq(pict_type,PICT_TYPE_I)'": Select only I-frames.
  • -fps_mode vfr: Specifies variable frame rate mode for keyframes.
  • -vsync vfr: Maintains synchronization by setting variable frame rate.
  • /root/keyframes_%03d.png: Output filename pattern.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.