AgentSkillsCN

collect

借助 yt-dlp 和 ffmpeg 下载 YouTube 视频,并提取帧,用于 YOLO 训练数据。当您需要从视频 URL 中采集帧时,此技能尤为实用。

SKILL.md
--- frontmatter
name: collect
description: Download YouTube videos and extract frames using yt-dlp and ffmpeg for YOLO training data. Use when you need to gather frames from a video URL.

Instructions

  1. Read config.json for video_url, fps, output_dir
  2. Run: uv run .agents/skills/collect/scripts/run.py
  3. Outputs: output/video.mp4, output/frames/frame_*.jpg