About ra-video-download
ra-video-download is a skill for acquiring source media in content-production workflows. It runs a bundled downloader, verifies that the resulting media is playable, and follows rules for storing source details and avoiding file overwrites.
Key features
- 01Downloads video or audio only
- 02Selects methods by supported site
- 03Checks playable streams and duration
- 04Stores source details and avoids overwrites
Use cases
- 01Acquire short videos as production references
- 02Download approved source media for a project
- 03Verify downloaded files and record media details
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ pluviobyte/ rnskill --skill ra-video-downloadAfter installing, type/ra-video-downloadin Claude Code to confirm it loaded.
Bundled filesagents/openai.yamlscripts/download_media.py
Details
From the project README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
- Confirm that the URL is source media and that downloading it is within the user's request.
- Run the bundled downloader. It uses this order:
- Douyin: TikHub media URL, then
yt-dlpwith browser cookies, then plainyt-dlp. - Other supported sites: plain
yt-dlp, optionally with browser cookies when required.
- Douyin: TikHub media URL, then
- Inspect the returned local path and media probe. A successful HTTP response alone is not delivery.
- Require a playable audio or video stream and a non-zero duration. Report the local path, duration, dimensions, and selected download method.
- 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.
/opt/homebrew/bin/python3 scripts/download_media.py '<url>'
Useful options:
# 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_KEYfrom 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
ffprobefails, reject the file even if it has an.mp4extension.
Handoff
Return a compact result containing:
- local media path
- source metadata path
- method used (
tikhub,yt-dlp-cookie, oryt-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.