Download Video

What it does

When your agent uses it

• Someone says download this video
• Save this video
• Grab the video from this page
• Provides a URL and asks to download media from it

Example prompts

• “download this video”
• “save this video”
• “grab the video from this page”
• “/download-video”

Requirements

• Python 3
• Compatibility (from SKILL.md): Requires macOS or Linux with yt-dlp installed (brew install yt-dlp). curl_cffi Python package recommended for impersonation support (pip3 install curl_cffi). Internet connection required.

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Fetch the Page and Identify the Video
2. 2Resolve the Download URL
3. 3Download with yt-dlp
4. 4Quality Selection (Optional)
5. 5Output Location

What it can do on your machine

Read from SKILL.md and the folder at commit 038ef34. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • yt-dlp
  • brew
  • pip3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • player.vimeo.com
  • vimeo.com
  • forum.openai.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires macOS or Linux with yt-dlp installed (brew install yt-dlp). curl_cffi Python package recommended for impersonation support (pip3 install curl_cffi). Internet connection required.

  From compatibility in the SKILL.md frontmatter.

Context cost

Download Video loads about 2k tokens when it runs. Until then it costs about 141 tokens; SKILL.md has 730 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~141

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from swyxio/skills at commit 038ef34, republished under its MIT licence (© swyxio). 730 words, ~2,003 tokens.

name

download-video

description

Downloads embedded videos from web pages. Fetches the page, identifies the video hosting service (Vimeo, YouTube, etc.), resolves the correct embed/player URL, and downloads using yt-dlp. Handles private/unlisted videos that require referer headers or embed URLs. Use this skill when someone says "download this video", "save this video", "grab the video from this page", "rip this video", or provides a URL and asks to download media from it. Also trigger when someone pastes a URL to a page with an embedded video and wants the video file locally.

compatibility

Requires macOS or Linux with yt-dlp installed (brew install yt-dlp). curl_cffi Python package recommended for impersonation support (pip3 install curl_cffi). Internet connection required.

license

MIT

metadata.author

swyxio

metadata.version

1.1

metadata.last-updated

2026-03-28

metadata.primary-tools

yt-dlp, WebFetch

which yt-dlp || brew install yt-dlp
brew upgrade yt-dlp

pip3 install --break-system-packages curl_cffi

https://player.vimeo.com/video/{id}?h={hash}

yt-dlp "https://player.vimeo.com/video/{id}"

yt-dlp --referer "{source_page_url}" "https://player.vimeo.com/video/{id}"

yt-dlp --referer "{source_page_url}" --add-header "Origin: {source_origin}" "https://player.vimeo.com/video/{id}"

yt-dlp "{video_url}"

# List available formats
yt-dlp -F "{url}"

# Download best quality (default)
yt-dlp -f "bestvideo+bestaudio" "{url}"

# Download specific resolution
yt-dlp -f "bestvideo[height<=1080]+bestaudio" "{url}"

# Download audio only
yt-dlp -f "bestaudio" -x --audio-format mp3 "{url}"

yt-dlp -o "~/Downloads/%(title)s.%(ext)s" "{url}"

ERROR: Failed to fetch OAuth token: HTTP Error 400: Bad Request

ERROR: Unable to download macos API JSON: HTTP Error 404: Not Found

ERROR: HTTP Error 403: Forbidden

yt-dlp --referer "{source_page_url}" "{embed_url}"

WARNING: The extractor is attempting impersonation, but no impersonate target is available

ERROR: This video is not available in your country

yt-dlp --proxy socks5://127.0.0.1:1080 "{url}"

# 1. Page has schema.org VideoObject with contentUrl: https://vimeo.com/1174947711
#    Direct URL fails (private video).

# 2. This works — use the player embed URL:
yt-dlp --referer "https://forum.openai.com/" "https://player.vimeo.com/video/1174947711"

# 3. yt-dlp downloads HLS fragments (484 in this case), merges video+audio.
#    Result: ~683MB MP4 file.

© swyxio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in download-video of swyxio/skills.

• SKILL.md
• README.md

Open the folder on GitHubat commit 038ef34