Video Downloader
Download videos from various platforms for offline viewing.
Install
npx skills add zyipeng/video-downloader --skill video-downloadergit clone --depth 1 https://github.com/zyipeng/video-downloader.git /tmp/video-downloader
mkdir -p ~/.claude/skills
cp -r /tmp/video-downloader/. ~/.claude/skills/video-downloaderPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
What this skill does
Downloads videos from YouTube and other platforms for offline use. Save videos locally for later viewing.
Trigger phrases
Claude loads this skill automatically when you say things like:
How it works
- Parse video URL
- Extract video stream
- Download to local storage
When to use it
- When saving videos offline
- For video archival
- When downloading content
From the SKILL.md
# Video Downloader
支持从多个视频平台下载视频到本地，基于 `yt-dlp` + 自研脚本实现。下载前先解析所有可下载档位让用户挑选，自动应用平台特定优化。
> 📘 **新用户必读**：完整安装 / 权限 / 路径配置见 [`SETUP.md`](./SETUP.md)。
> 📘 **平台细节 / 错误处理速查**：见 [`references/platform-notes.md`](./references/platform-notes.md)。
## Step 0：环境自检（首次使用必做）
```bash
MISSING=()
for tool in yt-dlp ffmpeg; do
command -v "$tool" >/dev/null 2>&1 || MISSING+=("$tool")
done
command -v aria2c >/dev/null 2>&1 || echo "ℹ️ aria2c 未装（可选，装了会快 10x）：brew install aria2"
if [[ ${#MISSING[@]} -gt 0 ]]; then
echo "❌ 缺少必需工具: ${MISSING[*]}"
echo " 请跑：brew install ${MISSING[*]}"
exit 1
fi
echo "✅ 必需工具齐全；默认下载目录：$HOME/Downloads"
```
依赖缺失时引导用户去 [`SETUP.md`](./SETUP.md)。
## 核心流程
### Step 1：识别下载请求并提取 URL
从用户消息中抽取**第一个**视频平台 URL。如果有多个 URL，逐个询问或批量处理。
### Step 2：识别平台 + 检查依赖
```bash
which yt-dlp ffmpeg aria2c 2>&1
```
平台特定的登录态 / cookies / 特殊脚本逻辑见 [`references/platform-notes.md`](./references/platform-notes.md)。下面只列出**影响交互**的关键提示：
- B 站 → 必须提示用户"720P+ 需要登录态"
- 小红书 → 必须确认 URL 含 `xsec_token`；`quality` 模式必须提示"4K 需要 Chrome 匿名 session cookie"
- 抖音 / 快手 → `download.sh` 会自动委派到对应专用脚本，无需 Agent 操心
- 微博 → `quality` 模式可能下到 300+ MB 大文件，提前告知
### Step 3：先探测，把档位给用户挑（**必须做**）
⚠️ **不要直接下载**。**必须**先调 probe 拿到档位表，让用户**自己选**。
**B 站 / 小红书 probe 前必须先问一句**（默认 guest 只能看 480p / 720p）：
> 想要 1080p+ 高清吗？需要读 Chrome 登录态 cookies（首次会弹一次 macOS 钥匙串，点「始终允许」即永久免弹）。**(1) 要高清** / **(2) 不用，guest 就行**
用户选 (1) → 命令前缀加 `VDL_USE_CHROME=1`；选 (2) 或其他平台 → 直接跑：Details
- Skill name
video-downloader- Repository
- zyipeng/video-downloader
- License
- MIT
- Repo updated
- 2 June 2026
FAQ
What does the Video Downloader skill do?
Downloads videos from YouTube and other platforms for offline use. Save videos locally for later viewing.
How do I install the Video Downloader skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add zyipeng/video-downloader --skill video-downloader. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Video Downloader popular?
It lives in zyipeng/video-downloader, which has 30 GitHub stars and 0 forks.
Related skills
Video Sharingan
23nikolasfaria/video-sharingan
Reverse-engineer the audiovisual production of a reference video (motion design, product launch, changelog, app promo, trailer) into measured numbers and a recreation brief. Use this when the user shares a video and says "make ours like this", "copy this style/camera/pacing", "what camera moves does this use", "how fast is the camera", "recreate this launch video", or before generating a video with Hyperframes, /brag, Remotion or After Effects from a reference. Measures cuts and shot durations, camera language (truck/pedestal/pan/push-in/pull-out/orbit, speed in px/s and %W/s, scale %/s, easin
Unblind
24Santazuki/unblind
Routes images to Mimo/OpenAI vision API for text-only models. Use this skill when the user sends an image, asks "what's in this picture", says "analyze this screenshot", requests "OCR" or "extract text", reviews UI designs, reads charts, or uses Chinese triggers like 识别图片/看图. Self-healing setup on first run. Does NOT handle video, audio, or PDFs.
Visual Multimedia
24CheshireMew/visual-multimedia
将确认内容制成可编辑、预览、导出的技术图解、GIF、HTML 动画、Live Photo、产品功能宣传片、其它视频、音频或播客，并处理文案。Use when the user asks to 制作网页视觉、剪辑或对齐实拍/访谈/录屏、为视频查找或添加免费可商用且不要求公开署名的 BGM、从本地视频或链接提取金句并制作字幕拼图、建立无需 Live2D 的二次元口播角色，或编辑音频与播客；不用于独立静态设计、PPTX、研究核查、长文、拍摄规划、账号运营或发布。
Seedance
27ye4wzp/seedance2.5-prompt-skill
Generate production-ready Chinese video prompts and image prompts for ByteDance Seedance 2.0 / 2.5 (即梦), and optionally execute them via the official dreamina CLI. Covers both versions — 2.0 (15s, 12 refs) and 2.5 (30s single-pass, up to 180s long-video mode, 50 refs, timestamp editing, green-screen reference, segment retake). Use when the user mentions "Seedance", "Seedance 2.5", "即梦", "即梦2.5", "小云雀", "豆包专业版", "30秒直出", "长视频模式", "片段重拍", "绿幕参考", "白模参考", "时间戳编辑", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", "角色图", "首帧图", "角色参考图", "生图", "运镜", "镜头", "景别", "机位", "推拉摇移", "四维编码", "Z轴", "Y轴", "X轴",
Awesome AI Product Video Workflows
21HiAPIAI/awesome-ai-video-workflows
Use when planning, creating, reviewing, or researching AI product videos from product images, ecommerce listings, or product briefs. Routes ecommerce sellers, ad teams, and AI creators through product-image preparation, hero visuals, storyboards, image-to-video generation, UGC ads, social variants, and media QC without inventing product claims.
Punk Ip Video Cover
24adrianpunk/punk-ip-video-cover
从上传人物照片提取四个颜色并搭配，抠出真人，按主题与标题自由构图，制作小红书人物 IP 视频封面；从独立库选择字体、材质与装饰风格，允许动作表情修改，支持 3:4、16:9、4:3、9:16 和多个版本。也用于接入新风格和编写封面提示词。
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.