Token导航 LogoToken导航TokenDH.com
待分类操作浏览器github未标认证来源可访问许可证需确认审计提醒

youtube-downloaderYouTube 下载器

Agent Skill

youtube-downloader 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

1,331

周安装

56

GitHub Stars

14

下载量

466
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:youtube-downloader(YouTube 下载器)
来源仓库:https://github.com/crazynomad/skills
仓库路径:skills/youtube-downloader
安装命令:
npx skills add https://github.com/crazynomad/skills --skill youtube-downloader
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/crazynomad/skills --skill youtube-downloader

简介

youtube-downloader 基于 yt-dlp 下载 YouTube 及百余家平台视频,支持格式选择与字幕抓取。

  • 适用于视频存档、音频提取或播放列表批量下载等多媒体资源获取场景。
  • 可指定分辨率、编码格式与元数据保留选项,支持代理与 Cookie 认证。
  • 需遵守目标平台服务条款,禁止用于侵权内容传播,建议使用私有网络环境。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

YouTube Video Downloader (yt-dlp)

Download videos from YouTube and 1000+ other sites using yt-dlp.

Description

A powerful video downloader skill based on yt-dlp that supports YouTube, Bilibili, Twitter/X, TikTok, and many other platforms. Features include format selection, audio extraction, subtitle download, playlist support, and metadata preservation.

When to Use

Use this skill when users:

  • Provide YouTube URLs and want to download videos
  • Mention "download video", "下载视频", "save video from YouTube"
  • Want to extract audio from videos (MP3)
  • Need to download playlists or channels
  • Want subtitles/captions from videos
  • Request video download from supported sites (Bilibili, Twitter, TikTok, etc.)

Features

  • Multi-Platform Support: YouTube, Bilibili, Twitter/X, TikTok, Vimeo, and 1000+ sites
  • Format Selection: Choose video quality (1080p, 720p, 4K) or audio-only
  • Audio Extraction: Extract audio as MP3, M4A, or other formats
  • Subtitle Download: Auto-download subtitles in multiple languages
  • Playlist Support: Download entire playlists or channels
  • Metadata Preservation: Save video info, thumbnails, and descriptions
  • Resume Support: Continue interrupted downloads
  • Progress Display: Real-time download progress

Usage

Basic Syntax

python scripts/download_video.py "VIDEO_URL" [OPTIONS]

Common Scenarios

Download single video (best quality):

python scripts/download_video.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ"

Download video in specific quality:

python scripts/download_video.py "https://www.youtube.com/watch?v=VIDEO_ID" -f 1080

Extract audio only (MP3):

python scripts/download_video.py "https://www.youtube.com/watch?v=VIDEO_ID" --audio-only

Download with subtitles:

python scripts/download_video.py "https://www.youtube.com/watch?v=VIDEO_ID" --subtitles

Download playlist:

python scripts/download_video.py "https://www.youtube.com/playlist?list=PLAYLIST_ID" --playlist

Download N videos from playlist:

python scripts/download_video.py "https://www.youtube.com/playlist?list=PLAYLIST_ID" --playlist -n 5

Specify output directory:

python scripts/download_video.py "URL" -o /path/to/output

Arguments

ArgumentDescriptionDefault
urlVideo/Playlist URL (required)-
-o, --outputOutput directoryCurrent directory
-f, --formatVideo quality: best, 1080, 720, 480, 360best
--audio-onlyExtract audio only (MP3)False
--subtitlesDownload subtitlesFalse
--sub-langSubtitle language(s)en,zh-Hans
--playlistEnable playlist downloadFalse
-n, --countNumber of videos from playlistAll
--metadataSave video metadata JSONTrue
--thumbnailDownload thumbnailFalse
--cookiesPath to cookies file (for age-restricted content)None

Dependencies

# Install yt-dlp
pip install yt-dlp --break-system-packages

# For audio extraction (optional)
# macOS
brew install ffmpeg

# Ubuntu/Debian
apt-get install ffmpeg

Output Structure

Single Video

OutputDir/
├── Video Title [VIDEO_ID].mp4     # Video file
├── Video Title [VIDEO_ID].json    # Metadata (if --metadata)
├── Video Title [VIDEO_ID].jpg     # Thumbnail (if --thumbnail)
└── Video Title [VIDEO_ID].en.vtt  # Subtitles (if --subtitles)

Playlist

OutputDir/
└── PlaylistName/
    ├── playlist_info.json
    ├── 001 - Video Title.mp4
    ├── 001 - Video Title.json
    ├── 002 - Another Video.mp4
    └── ...

Metadata Example

{
  "title": "Video Title",
  "uploader": "Channel Name",
  "upload_date": "2024-01-15",
  "duration": 300,
  "view_count": 1000000,
  "description": "Video description...",
  "tags": ["tag1", "tag2"],
  "video_file": "Video Title [VIDEO_ID].mp4"
}

Claude Integration

When user requests video download:

  1. Read skill documentation: view("/mnt/skills/user/youtube-downloader/SKILL.md")
  2. Install dependencies (if needed): pip install yt-dlp --break-system-packages
  3. Execute download: python /mnt/skills/user/youtube-downloader/scripts/download_video.py \ "USER_URL" -o /mnt/user-data/outputs
  4. Present files to user: present_files(["/mnt/user-data/outputs/..."])

Supported Platforms

Major Platforms

  • YouTube: Videos, Shorts, Playlists, Channels, Live streams
  • Bilibili: Videos, Episodes (may need cookies)
  • Twitter/X: Video tweets
  • TikTok: Videos (may need cookies)
  • Vimeo: Videos
  • Twitch: VODs, Clips

Full List

yt-dlp supports 1000+ sites. Run yt-dlp --list-extractors for full list.

Common Issues

Q: Age-restricted videos? A: Use --cookies with exported browser cookies: --cookies cookies.txt

Q: Format not available? A: Some videos may not have all quality options. Script will auto-select best available.

Q: Download speed slow? A: This is usually server-side throttling. Consider using a VPN or waiting.

Q: Need to login for private videos? A: Export cookies from your browser after logging in, then use --cookies.

Q: Audio extraction fails? A: Install ffmpeg: brew install ffmpeg (macOS) or apt install ffmpeg (Linux)

Example Conversations

User: "帮我下载这个 YouTube 视频: https://www.youtube.com/watch?v=dQw4w9WgXcQ"

Claude:

# Install yt-dlp
pip install yt-dlp --break-system-packages

# Download video
python /mnt/skills/user/youtube-downloader/scripts/download_video.py \
  "https://www.youtube.com/watch?v=dQw4w9WgXcQ" \
  -o /mnt/user-data/outputs

# Present files
present_files([...])

User: "下载这个 YouTube 视频的音频,我只要 MP3"

Claude:

python /mnt/skills/user/youtube-downloader/scripts/download_video.py \
  "VIDEO_URL" \
  --audio-only \
  -o /mnt/user-data/outputs

User: "Download this playlist, but only the first 5 videos"

Claude:

python /mnt/skills/user/youtube-downloader/scripts/download_video.py \
  "PLAYLIST_URL" \
  --playlist -n 5 \
  -o /mnt/user-data/outputs

How It Works

Workflow

  1. URL Parsing: Detect platform and content type (video/playlist)
  2. Format Selection: Determine best available format based on user preference
  3. Download: Stream video/audio with progress display
  4. Post-Processing: Extract audio (if requested), embed subtitles
  5. Metadata: Save video information to JSON

Under the Hood

This skill wraps yt-dlp with sensible defaults:

  • Automatic format selection for best quality
  • Proper filename sanitization
  • Retry logic for failed downloads
  • Progress display with ETA

Limitations

  • Some sites may require authentication (cookies)
  • Age-restricted content needs browser cookies
  • Download speed depends on source server
  • Some DRM-protected content cannot be downloaded
  • Live streams can only be downloaded after they end (VOD)

Legal Notice

This tool is for personal use only. Please respect:

  • YouTube Terms of Service
  • Copyright laws in your jurisdiction
  • Content creators' rights

Only download content you have the right to access. Do not redistribute copyrighted material.

Version History

v1.0 (Current)

  • Initial release with yt-dlp wrapper
  • Support for video, audio, subtitles, playlists
  • Metadata and thumbnail preservation
  • Multi-platform support

References

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.37%
按下载量换算165

Claude

34.88%
按下载量换算163

Cursor

17.87%
按下载量换算83

Gemini CLI

9.55%
按下载量换算45

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills