Ra Video Download logo

Ra Video Download

CommunityPopular
Pluviobyte
ra-video-download

Download source video or audio from Douyin, YouTube, Bilibili, Twitter/X, Xiaohongshu, and other yt-dlp-supported URLs into the content-creation workspace. Use when the user says 下载视频, 下载音频, 保存这个链接, 把源视频拉下来, or when another video workflow needs a local source file before transcription, frame analysis, editing, reference replication, or archiving.

Overview

PublisherPluviobyte
Repositoryrnskill
Skill namera-video-download
Stars
1.6K
Forks
181
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Pluviobyte on GitHub. Read the source before you install it.

Installation

Install the Ra Video Download AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Pluviobyte/rnskill.git /tmp/rnskill
mkdir -p .claude/skills
cp -r /tmp/rnskill/skills/ra-video-download .claude/skills/ra-video-download
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ra Video Download in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ra Video Download on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ra Video Download is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

视频下载

Download source media only. Do not transcribe, rewrite, edit, or publish it.

Storage rules

  • Keep source URLs, source titles, source metadata, and downloaded reference media inside 01-内容生产/视频工作台/.internal/ by default.
  • Use 01-内容生产/视频工作台/制作中/<日期-主题>/原始素材/ only when the caller explicitly names a production project and the media is an approved production input.
  • Never place source information in a handoff, finished script, final archive, or public document.
  • Never overwrite an existing file. Let the downloader add a stable suffix or stop.

Workflow

  1. Confirm that the URL is source media and that downloading it is within the user's request.
  2. Run the bundled downloader. It uses this order:
    • Douyin: TikHub media URL, then yt-dlp with browser cookies, then plain yt-dlp.
    • Other supported sites: plain yt-dlp, optionally with browser cookies when required.
  3. Inspect the returned local path and media probe. A successful HTTP response alone is not delivery.
  4. Require a playable audio or video stream and a non-zero duration. Report the local path, duration, dimensions, and selected download method.
  5. If every route fails, preserve the concise failure log and state the missing prerequisite. Do not claim that the video was downloaded.

Command

Use the Python interpreter that can import tikhub for the best Douyin path. In this workspace, prefer /opt/homebrew/bin/python3 when available.

bash
/opt/homebrew/bin/python3 scripts/download_media.py '<url>'

Useful options:

bash
# Explicit production input directory
/opt/homebrew/bin/python3 scripts/download_media.py '<url>' --output-dir '01-内容生产/视频工作台/制作中/<日期-主题>/原始素材/<项目>'

# Extract audio only
/opt/homebrew/bin/python3 scripts/download_media.py '<url>' --audio-only

# Use an authenticated browser profile for a protected public page
/opt/homebrew/bin/python3 scripts/download_media.py '<url>' --cookies-from-browser chrome

Resolve scripts/download_media.py relative to this SKILL.md; do not assume the current directory is the skill directory.

Safety and failure handling

  • Use browser cookies only for the requested public media. Do not print, copy, or persist raw cookies.
  • Read TIKHUB_API_KEY from the environment or the workspace-root .env; never print it.
  • Do not bypass private-account access controls, paywalls, DRM, or deleted/private media.
  • Treat TikHub and browser cookies as acquisition fallbacks, not as proof that reuse rights exist.
  • Keep the original source file untouched after download.
  • If ffprobe fails, reject the file even if it has an .mp4 extension.

Handoff

Return a compact result containing:

  • local media path
  • source metadata path
  • method used (tikhub, yt-dlp-cookie, or yt-dlp)
  • duration, resolution, and codecs
  • any limitation such as watermark, missing audio, or authentication failure

Then route onward only when requested: ra-逐字稿提取skill for source speech extraction, video-use for editing, or ra-video-production-director for production.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ra Video Download AI skill do?

Download source video or audio from Douyin, YouTube, Bilibili, Twitter/X, Xiaohongshu, and other yt-dlp-supported URLs into the content-creation workspace. Use when the user says 下载视频, 下载音频, 保存这个链接, 把源视频拉下来, or when another video workflow needs a local source file before transcription, frame analysis, editing, reference replication, or archiving.

Why use Ra Video Download on TypingMind?

Because you install it once and use it with any model. Ra Video Download is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ra Video Download in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Pluviobyte/rnskill/tree/main/skills/ra-video-download. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ra Video Download?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ra Video Download?

As many as you like. As long as a model supports skills, you can use Ra Video Download with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ra Video Download AI skill free?

It is published on GitHub by Pluviobyte. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇