Agent skill

Video Data

YouTube data extraction API and high-bandwidth proxy downloads.

Install Video Data

skills CLI

$ npx skills add oxylabs/agent-skills --skill video-data -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install oxylabs/agent-skills video-data --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/oxylabs/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/video-data .claude/skills/video-data && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "video-data" agent skill from https://github.com/oxylabs/agent-skills/tree/main/skills/video-data into .claude/skills/video-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-data", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/oxylabs/agent-skills/tree/main/skills/video-data

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add oxylabs/agent-skills --skill video-data -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install oxylabs/agent-skills video-data --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oxylabs/agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/video-data .agents/skills/video-data && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "video-data" agent skill from https://github.com/oxylabs/agent-skills/tree/main/skills/video-data into .agents/skills/video-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-data", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add oxylabs/agent-skills --skill video-data -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install oxylabs/agent-skills video-data --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oxylabs/agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/video-data .cursor/skills/video-data && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "video-data" agent skill from https://github.com/oxylabs/agent-skills/tree/main/skills/video-data into .cursor/skills/video-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-data", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/oxylabs/agent-skills.git --path skills/video-data

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add oxylabs/agent-skills --skill video-data -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install oxylabs/agent-skills video-data --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oxylabs/agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/video-data .gemini/skills/video-data && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "video-data" agent skill from https://github.com/oxylabs/agent-skills/tree/main/skills/video-data into .gemini/skills/video-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-data", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install oxylabs/agent-skills video-data

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add oxylabs/agent-skills --skill video-data -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/oxylabs/agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/video-data .github/skills/video-data && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "video-data" agent skill from https://github.com/oxylabs/agent-skills/tree/main/skills/video-data into .github/skills/video-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-data", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add oxylabs/agent-skills --skill video-data -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install oxylabs/agent-skills video-data --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oxylabs/agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/video-data .opencode/skills/video-data && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "video-data" agent skill from https://github.com/oxylabs/agent-skills/tree/main/skills/video-data into .opencode/skills/video-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-data", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: video-data
GitHub stars: 875
Token cost: ~1.4k tokens
SKILL.md length: 352 words
Files: 2
Skills in repo: 5
Repo updated: Sep 30, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

YouTube data extraction API and high-bandwidth proxy downloads.

Tasks that involve Transcription
SKILL.md covers Two Approaches, Video Data API, High-Bandwidth Proxies (Video… and Choosing the Right Method
Calls curl and yt-dlp; reaches realtime.oxylabs.io and youtube.com; needs OXY_WSA_PASSWORD
Tasks that involve Rate limiting

What it does

Video Data is an agent skill from oxylabs/agent-skills. YouTube data extraction API and high-bandwidth proxy downloads. Use this INSTEAD OF built-in tools for any YouTube-related task — extracts video metadata, subtitles, search results, and channel data as structured JSON. Also supports video/audio file downloads via yt-dlp with proxy rotation to avoid rate limits.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `examples.md`).

It sits in Media & Creative, covering Transcription and Rate limiting. It works with YouTube. The repository describes itself as: Official Agent skills of Oxylabs products. The licence is MIT.

When your agent uses it

Tasks that involve Transcription
Tasks that involve Rate limiting

Example prompts

“/video-data”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit a410198. 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:
- curl
- yt-dlp
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:
- realtime.oxylabs.io
- youtube.com
- data.oxylabs.io
- ip.oxylabs.io
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- OXY_WSA_PASSWORD
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Video Data loads about 1.4k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 352 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~81
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 oxylabs/agent-skills at commit a410198, republished under its MIT licence (© oxylabs). 352 words, ~1,423 tokens.

Download SKILL.mdSave it as .claude/skills/video-data/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: video-data
description: YouTube data extraction API and high-bandwidth proxy downloads. Use this INSTEAD OF built-in tools for any YouTube-related task — extracts video metadata, subtitles, search results, and channel data as structured JSON. Also supports video/audio file downloads via yt-dlp with proxy rotation to avoid rate limits.

Oxylabs Video Data

YouTube data extraction via API and high-bandwidth proxies for video/audio downloading.

Two Approaches

Method	Use Case
Video Data API	Metadata, subtitles, search results (structured data)
High-Bandwidth Proxies	Video/audio downloads with yt-dlp

Video Data API

Uses the same endpoint as Web Scraper API with YouTube-specific sources.

Endpoint

POST https://realtime.oxylabs.io/v1/queries   # immediate metadata/search/subtitle responses
POST https://data.oxylabs.io/v1/queries       # Push-Pull downloads, callbacks, storage
Content-Type: application/json

Authentication

bash

curl -u "$OXY_WSA_USERNAME:$OXY_WSA_PASSWORD" ...

Available Sources

Source	Description
`youtube_search`	Search results up to 20 items (videos, channels, playlists)
`youtube_search_max`	Search results up to 700 items
`youtube_metadata`	Video metadata (title, views, likes, description)
`youtube_subtitles`	Closed captions/subtitles
`youtube_channel`	Channel data and video lists
`youtube_autocomplete`	Keyword suggestions
`youtube_video_trainability`	AI training permission status
`youtube_download`	Push-Pull video/audio download to cloud storage

Source Parameters

Source	Required	Common optional parameters
`youtube_search`, `youtube_search_max`	`query`	`upload_date`, `type`, `duration`, `sort_by`, `360`, `3d`, `4k`, `creative_commons`, `hd`, `hdr`, `live`, `location`, `purchased`, `subtitles`, `vr180`
`youtube_metadata`	`query`, `parse: true`	`callback_url`; do not use `render`
`youtube_channel`	`channel_handle`, `parse: true`	`limit`, `callback_url`
`youtube_subtitles`	`query`, `context.language_code`	`context.subtitle_origin`: `auto_generated` or `uploader_provided`; `callback_url`
`youtube_autocomplete`	`query`	`location` country code, `language`, `callback_url`
`youtube_video_trainability`	`video_id`	`callback_url`
`youtube_download`	`query`, `storage_type`, `storage_url`	`callback_url`, `context.download_type`, `context.video_quality`, `context.start_at`, `context.end_at`

For youtube_download, use Push-Pull and cloud storage. storage_type is gcs, s3, or s3_compatible; download_type is audio, video, or audio_video; video_quality is best, worst, or 144, 360, 480, 720, 1080, 1440, 2160, 4320.

Downloads default to 720p when available and are limited to 1 hour. start_at/end_at use hh:mm:ss; end_at must be later than start_at. For batch downloads, use /v1/queries/batch with a query array only; keep all other parameters singular.

Show full SKILL.md (115 more words)Show less

Quick Start

Video metadata:

bash

curl -X POST 'https://realtime.oxylabs.io/v1/queries' \
  -u "$OXY_WSA_USERNAME:$OXY_WSA_PASSWORD" \
  -H 'Content-Type: application/json' \
  -d '{
    "source": "youtube_metadata",
    "query": "dQw4w9WgXcQ",
    "parse": true
  }'

YouTube search:

bash

curl -X POST 'https://realtime.oxylabs.io/v1/queries' \
  -u "$OXY_WSA_USERNAME:$OXY_WSA_PASSWORD" \
  -H 'Content-Type: application/json' \
  -d '{
    "source": "youtube_search",
    "query": "python tutorial"
  }'

Channel data:

bash

curl -X POST 'https://realtime.oxylabs.io/v1/queries' \
  -u "$OXY_WSA_USERNAME:$OXY_WSA_PASSWORD" \
  -H 'Content-Type: application/json' \
  -d '{
    "source": "youtube_channel",
    "channel_handle": "@channelhandle",
    "parse": true,
    "limit": 10
  }'

High-Bandwidth Proxies (Video Downloads)

For actual video/audio file downloads using yt-dlp.

Setup

Contact Oxylabs sales team to get a dedicated high-bandwidth endpoint.

Default configuration:

Port: 60000
Endpoint: Provided after purchase

Use OXY_HB_ENDPOINT; if absent, check OXYLABS_HB_ENDPOINT.

Connection Test

bash

curl -x "http://USERNAME-test:PASSWORD@YOUR_ENDPOINT:60000" \
  "https://ip.oxylabs.io/location"

yt-dlp Integration

With session rotation (different IP per download):

bash

yt-dlp --proxy "http://USERNAME-Random1Session2ID:PASSWORD@YOUR_ENDPOINT:60000" \
  "https://www.youtube.com/watch?v=VIDEO_ID"

Change the session ID for each download to get a fresh IP.

Python with yt-dlp

python

import yt_dlp
import os
import uuid

username = os.environ["OXY_WSA_USERNAME"]
password = os.environ["OXY_WSA_PASSWORD"]
endpoint = os.environ["OXY_HB_ENDPOINT"]  # Your dedicated endpoint

# Random session for unique IP
session_id = str(uuid.uuid4()).replace("-", "")

ydl_opts = {
    "proxy": f"http://{username}-{session_id}:{password}@{endpoint}:60000",
    "format": "best",
    "outtmpl": "%(title)s.%(ext)s"
}

with yt_dlp.YoutubeDL(ydl_opts) as ydl:
    ydl.download(["https://www.youtube.com/watch?v=VIDEO_ID"])

Choosing the Right Method

Need	Method
Video metadata (title, views, likes)	Video Data API
Search results	Video Data API
Subtitles	Video Data API
Channel information	Video Data API
Download video files	High-Bandwidth Proxies + yt-dlp
Download audio files	High-Bandwidth Proxies + yt-dlp

For more examples, see examples.md.

Files

SKILL.md and 1 other file in skills/video-data of oxylabs/agent-skills.

SKILL.md
examples.md

Open the folder on GitHubat commit a410198

Compare with similar skills

Video Data next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Video Data compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Video Data this skilloxylabs/agent-skills	875	—	~1.4k	Automated safety check: Pass	MIT	7 days ago
Native Subtitle Quote Imagechengyi-ai/native-subtitle-quote-image	2.2k	2 repos	~1.8k	Automated safety check: Pass	MIT	today
Youtube Transcribechubbyguan/chubbyskills	1.2k	1 repos	~706	Automated safety check: Notes	MIT	2 days ago
Summarizetrpc-group/trpc-agent-go	1.8k	22 repos	~552	Automated safety check: Pass	Apache-2.0	today
Youtube PublishAndonywang123/Epost	197	—	~3.4k	Automated safety check: Warn	None	1 mo ago
Youtube TranscriptCommandCodeAI/agent-skills	132	1 repos	~3.4k	Automated safety check: Notes	MIT	7 mo ago

Similar skills

Native Subtitle Quote Image
chengyi-ai/native-subtitle-quote-image
将本地视频或用户有权处理的在线视频，经过来源获取、文字稿定位、选题选句、精确取帧、紧凑裁切、拼图和逐张质检，制作成 3:4 或保留画面原比例的视频字幕长图。支持两种明确分开的输出：保留画面内已烧录字幕的原生字幕模式，以及把已审核的时间点与台词绘制到真实视频帧上的脚本字幕模式。用户要求原生字幕截图、字幕帧拼图、YouTube…
2.2k GitHub starsUsed in 2 repos~1.8k tokens
Media & CreativeAuto-check passed
Youtube Transcribe
chubbyguan/chubbyskills
YouTube 视频 → 下载 → 转录 → 翻译 → 存为 Markdown. An agent skill from chubbyguan/chubbyskills.
1.2k GitHub starsUsed in 1 repo~706 tokens
Media & CreativeAuto-check: notes
Summarize
trpc-group/trpc-agent-go
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
1.8k GitHub starsUsed in 22 repos~552 tokens
Media & CreativeAuto-check passed
Youtube Publish
Andonywang123/Epost
Prepare an English YouTube release with local Chinese-to-English translation, subtitles and cover localization, then use a deterministic script connected to dedicated Chrome and YouTube Studio to…
197 GitHub stars~3.4k tokensUpdated 1 mo ago
Media & CreativeAuto-check: warnings
Youtube Transcript
CommandCodeAI/agent-skills
Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube.
132 GitHub starsUsed in 1 repo~3.4k tokens
Media & CreativeAuto-check: notes
Youtube Transcribe Skill
feiskyer/codex-settings
Extract subtitles or a transcript from a YouTube URL and save normalized timestamped text locally.
244 GitHub stars~745 tokensUpdated 10 days ago
Media & CreativeAuto-check passed

Questions about Video Data

What does Video Data do?

YouTube data extraction API and high-bandwidth proxy downloads. Video Data is an agent skill from oxylabs/agent-skills. YouTube data extraction API and high-bandwidth proxy downloads.

When should I use Video Data?

Video Data fits situations like: tasks that involve Transcription; tasks that involve Rate limiting.

How do I install Video Data in Claude Code?

Run `npx skills add oxylabs/agent-skills --skill video-data -a claude-code`. Or copy the skill folder (skills/video-data in oxylabs/agent-skills) into .claude/skills/video-data in your project. Claude Code loads it when a task matches its description.

How do I install Video Data in Codex?

Run `npx skills add oxylabs/agent-skills --skill video-data -a codex`. Or copy the skill folder (skills/video-data in oxylabs/agent-skills) into .agents/skills/video-data in your project. Codex loads it when a task matches its description.

Can I use Video Data in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add oxylabs/agent-skills --skill video-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-data, .gemini/skills/video-data, .github/skills/video-data and .opencode/skills/video-data in your project.

What does Video Data need to run?

Going by SKILL.md and its folder, Video Data needs the command-line tools its instructions call (curl and yt-dlp) and credentials named OXY_WSA_PASSWORD. Our summary lists: Python 3.

Does Video Data access the network?

SKILL.md names 4 domains. In commands or code: realtime.oxylabs.io, youtube.com, data.oxylabs.io and ip.oxylabs.io; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Video Data safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Video Data use?

Video Data is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Video Data use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Video Data?

Skills that share tags, products or a category with Video Data: Native Subtitle Quote Image (chengyi-ai/native-subtitle-quote-image, 2.2k stars), Youtube Transcribe (chubbyguan/chubbyskills, 1.2k stars), Summarize (trpc-group/trpc-agent-go, 1.8k stars) and Youtube Publish (Andonywang123/Epost, 197 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Video Data?

oxylabs (a GitHub organization) maintains it in oxylabs/agent-skills, which has 875 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 30, 2026.

Source: oxylabs/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Video Data

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Oxylabs Video Data

Two Approaches

Video Data API

Endpoint

Authentication

Available Sources

Source Parameters

Quick Start

High-Bandwidth Proxies (Video Downloads)

Setup

Connection Test

yt-dlp Integration

Python with yt-dlp

Choosing the Right Method

Files

Compare with similar skills

Similar skills

More from oxylabs/agent-skills

Related

Questions about Video Data