Token导航 LogoToken导航

Agent Skill · 研究检索

youtube(YouTube 视频)

youtube 用于查找、检索和筛选相关信息,适合在 Local Agent 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

youtube 是研究检索类 Agent Skill,可用宿主为 Local Agent,通过unknown获取,权限为接触敏感数据;许可证信息还不明确,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 59,000。

总安装 396周安装 17下载 139核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:youtube(YouTube 视频)
来源仓库:https://skills.volces.com
仓库路径:youtube
安装命令:
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。当前暂无明确安装命令,请以来源页面说明为准。

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

youtube 用于 YouTube 视频内容的检索与信息提取。适合在 Local Agent 中查找视频元数据、频道信息或播放列表。可通过关键词搜索相关视频,具体接口请参考原始文档。使用前需确认是否具备公网访问能力及遵守 YouTube API 配额。注意内容版权,避免用于非法分发或商业盗用场景。

来源仓库内路径:youtube

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Local Agent;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    没有现成安装命令,按unknown的说明从来源页面获取,仓库路径是 youtube。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

youtube 怎么安装?

公开资料没有给出可以直接复制的命令,需要按来源页面说明手动安装,仓库内路径为 youtube。

youtube 支持哪些 AI 工具?

公开资料标注支持 Local Agent。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

youtube 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

youtube 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

youtube 用的人多吗?

公开数据是累计安装 396 次,近一周安装 17 次,下载 139 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

youtube 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 Local Agent 一种宿主,触发方式和使用习惯不用来回切换。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Local Agent,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 要求有安全扫描结论才肯安装的团队。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
youtube

YouTube 视频 · 本页

396—接触敏感数据未明确未收录

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

YouTube

Access the YouTube Data API v3 with managed OAuth authentication. Search videos, manage playlists, access channel information, and interact with comments and subscriptions.

Quick Start

# Search for videos
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://gateway.maton.ai/youtube/youtube/v3/search?part=snippet&q=coding+tutorial&type=video&maxResults=10')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Base URL

https://gateway.maton.ai/youtube/{native-api-path}

Replace {native-api-path} with the actual YouTube Data API endpoint path. The gateway proxies requests to www.googleapis.com and automatically injects your OAuth token.

Authentication

All requests require the Maton API key in the Authorization header:

Authorization: Bearer $MATON_API_KEY

Environment Variable: Set your API key as MATON_API_KEY:

export MATON_API_KEY="YOUR_API_KEY"

Getting Your API Key

  1. Sign in or create an account at maton.ai
  2. Go to maton.ai/settings
  3. Copy your API key

Connection Management

Manage your Google OAuth connections at https://ctrl.maton.ai.

List Connections

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections?app=youtube&status=ACTIVE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Create Connection

python <<'EOF'
import urllib.request, os, json
data = json.dumps({'app': 'youtube'}).encode()
req = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Get Connection

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Response:

{
  "connection": {
    "connection_id": "21fd90f9-5935-43cd-b6c8-bde9d915ca80",
    "status": "ACTIVE",
    "creation_time": "2025-12-08T07:20:53.488460Z",
    "last_updated_time": "2026-01-31T20:03:32.593153Z",
    "url": "https://connect.maton.ai/?session_token=...",
    "app": "youtube",
    "metadata": {}
  }
}

Open the returned url in a browser to complete OAuth authorization.

Delete Connection

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Specifying Connection

If you have multiple YouTube connections, specify which one to use with the Maton-Connection header:

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://gateway.maton.ai/youtube/youtube/v3/channels?part=snippet&mine=true')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Maton-Connection', '21fd90f9-5935-43cd-b6c8-bde9d915ca80')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

If omitted, the gateway uses the default (oldest) active connection.

API Reference

Search

Search Videos, Channels, or Playlists
GET /youtube/youtube/v3/search

Query parameters:

  • part - Required: snippet
  • q - Search query
  • type - Filter by type: video, channel, playlist
  • maxResults - Results per page (1-50, default 5)
  • order - Sort order: date, rating, relevance, title, viewCount
  • publishedAfter - Filter by publish date (RFC 3339)
  • publishedBefore - Filter by publish date (RFC 3339)
  • channelId - Filter by channel
  • videoDuration - short (<4min), medium (4-20min), long (>20min)
  • pageToken - Pagination token

Example:

curl -s -X GET "https://gateway.maton.ai/youtube/youtube/v3/search?part=snippet&q=machine+learning&type=video&maxResults=10&order=viewCount" -H "Authorization: Bearer $MATON_API_KEY"

Response:

{
  "kind": "youtube#searchListResponse",
  "nextPageToken": "CAUQAA",
  "pageInfo": {
    "totalResults": 1000000,
    "resultsPerPage": 10
  },
  "items": [
    {
      "kind": "youtube#searchResult",
      "id": {
        "kind": "youtube#video",
        "videoId": "abc123xyz"
      },
      "snippet": {
        "publishedAt": "2024-01-15T10:00:00Z",
        "channelId": "UCxyz123",
        "title": "Machine Learning Tutorial",
        "description": "Learn ML basics...",
        "thumbnails": {
          "default": {"url": "https://i.ytimg.com/vi/abc123xyz/default.jpg"}
        },
        "channelTitle": "Tech Channel"
      }
    }
  ]
}

Videos

Get Video Details
GET /youtube/youtube/v3/videos?part=snippet,statistics,contentDetails&id={videoId}

Parts available:

  • snippet - Title, description, thumbnails, channel info
  • statistics - View count, likes, comments
  • contentDetails - Duration, dimension, definition
  • status - Upload status, privacy status
  • player - Embedded player HTML

Example:

curl -s -X GET "https://gateway.maton.ai/youtube/youtube/v3/videos?part=snippet,statistics&id=dQw4w9WgXcQ" -H "Authorization: Bearer $MATON_API_KEY"
Get My Videos (Uploaded)
GET /youtube/youtube/v3/search?part=snippet&forMine=true&type=video&maxResults=25
Rate Video (Like/Dislike)
POST /youtube/youtube/v3/videos/rate?id={videoId}&rating=like

Rating values: like, dislike, none

Get Trending Videos
GET /youtube/youtube/v3/videos?part=snippet,statistics&chart=mostPopular&regionCode=US&maxResults=10
Get Video Categories
GET /youtube/youtube/v3/videoCategories?part=snippet&regionCode=US

Channels

Get Channel Details
GET /youtube/youtube/v3/channels?part=snippet,statistics,contentDetails&id={channelId}
Get My Channel
GET /youtube/youtube/v3/channels?part=snippet,statistics,contentDetails&mine=true

Response:

{
  "items": [
    {
      "id": "UCxyz123",
      "snippet": {
        "title": "My Channel",
        "description": "Channel description",
        "customUrl": "@mychannel",
        "publishedAt": "2020-01-01T00:00:00Z",
        "thumbnails": {...}
      },
      "statistics": {
        "viewCount": "1000000",
        "subscriberCount": "50000",
        "videoCount": "100"
      },
      "contentDetails": {
        "relatedPlaylists": {
          "uploads": "UUxyz123"
        }
      }
    }
  ]
}
Get Channel by Username
GET /youtube/youtube/v3/channels?part=snippet,statistics&forUsername={username}

Playlists

List My Playlists
GET /youtube/youtube/v3/playlists?part=snippet,contentDetails&mine=true&maxResults=25
Get Playlist
GET /youtube/youtube/v3/playlists?part=snippet,contentDetails&id={playlistId}
Create Playlist
POST /youtube/youtube/v3/playlists?part=snippet,status
Content-Type: application/json

{
  "snippet": {
    "title": "My New Playlist",
    "description": "A collection of videos",
    "defaultLanguage": "en"
  },
  "status": {
    "privacyStatus": "private"
  }
}

Privacy values: public, private, unlisted

Update Playlist
PUT /youtube/youtube/v3/playlists?part=snippet,status
Content-Type: application/json

{
  "id": "PLxyz123",
  "snippet": {
    "title": "Updated Playlist Title",
    "description": "Updated description"
  },
  "status": {
    "privacyStatus": "public"
  }
}
Delete Playlist
DELETE /youtube/youtube/v3/playlists?id={playlistId}

Playlist Items

List Playlist Items
GET /youtube/youtube/v3/playlistItems?part=snippet,contentDetails&playlistId={playlistId}&maxResults=50
Add Video to Playlist
POST /youtube/youtube/v3/playlistItems?part=snippet
Content-Type: application/json

{
  "snippet": {
    "playlistId": "PLxyz123",
    "resourceId": {
      "kind": "youtube#video",
      "videoId": "abc123xyz"
    },
    "position": 0
  }
}
Remove from Playlist
DELETE /youtube/youtube/v3/playlistItems?id={playlistItemId}

Subscriptions

List My Subscriptions
GET /youtube/youtube/v3/subscriptions?part=snippet&mine=true&maxResults=50
Check Subscription to Channel
GET /youtube/youtube/v3/subscriptions?part=snippet&mine=true&forChannelId={channelId}
Subscribe to Channel
POST /youtube/youtube/v3/subscriptions?part=snippet
Content-Type: application/json

{
  "snippet": {
    "resourceId": {
      "kind": "youtube#channel",
      "channelId": "UCxyz123"
    }
  }
}
Unsubscribe
DELETE /youtube/youtube/v3/subscriptions?id={subscriptionId}

Comments

List Video Comments
GET /youtube/youtube/v3/commentThreads?part=snippet,replies&videoId={videoId}&maxResults=100
Add Comment to Video
POST /youtube/youtube/v3/commentThreads?part=snippet
Content-Type: application/json

{
  "snippet": {
    "videoId": "abc123xyz",
    "topLevelComment": {
      "snippet": {
        "textOriginal": "Great video!"
      }
    }
  }
}
Reply to Comment
POST /youtube/youtube/v3/comments?part=snippet
Content-Type: application/json

{
  "snippet": {
    "parentId": "comment123",
    "textOriginal": "Thanks for your comment!"
  }
}
Delete Comment
DELETE /youtube/youtube/v3/comments?id={commentId}

Code Examples

JavaScript

const headers = {
  'Authorization': `Bearer ${process.env.MATON_API_KEY}`
};

// Search videos
const results = await fetch(
  'https://gateway.maton.ai/youtube/youtube/v3/search?part=snippet&q=tutorial&type=video&maxResults=10',
  { headers }
).then(r => r.json());

// Get video details
const video = await fetch(
  'https://gateway.maton.ai/youtube/youtube/v3/videos?part=snippet,statistics&id=dQw4w9WgXcQ',
  { headers }
).then(r => r.json());

// Create playlist
await fetch(
  'https://gateway.maton.ai/youtube/youtube/v3/playlists?part=snippet,status',
  {
    method: 'POST',
    headers: { ...headers, 'Content-Type': 'application/json' },
    body: JSON.stringify({
      snippet: { title: 'My Playlist', description: 'Videos I like' },
      status: { privacyStatus: 'private' }
    })
  }
);

Python

import os
import requests

headers = {'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}'}

# Search videos
results = requests.get(
    'https://gateway.maton.ai/youtube/youtube/v3/search',
    headers=headers,
    params={'part': 'snippet', 'q': 'tutorial', 'type': 'video', 'maxResults': 10}
).json()

# Get video details
video = requests.get(
    'https://gateway.maton.ai/youtube/youtube/v3/videos',
    headers=headers,
    params={'part': 'snippet,statistics', 'id': 'dQw4w9WgXcQ'}
).json()

# Create playlist
response = requests.post(
    'https://gateway.maton.ai/youtube/youtube/v3/playlists?part=snippet,status',
    headers=headers,
    json={
        'snippet': {'title': 'My Playlist', 'description': 'Videos I like'},
        'status': {'privacyStatus': 'private'}
    }
)

Notes

  • Video IDs are 11 characters (e.g., dQw4w9WgXcQ)
  • Channel IDs start with UC (e.g., UCxyz123)
  • Playlist IDs start with PL (user) or UU (uploads)
  • Use pageToken for pagination through large result sets
  • The part parameter is required and determines what data is returned
  • Quota costs vary by endpoint - search is expensive (100 units), reads are cheap (1 unit)
  • Some write operations require channel verification
  • IMPORTANT: When using curl commands, use curl -g when URLs contain brackets (fields[], sort[], records[]) to disable glob parsing
  • IMPORTANT: When piping curl output to jq or other commands, environment variables like $MATON_API_KEY may not expand correctly in some shell environments. You may get "Invalid API key" errors when piping.

Error Handling

StatusMeaning
400Missing YouTube connection or invalid request
401Invalid or missing Maton API key
403Forbidden - quota exceeded or insufficient permissions
404Video, channel, or playlist not found
429Rate limited (10 req/sec per account)
4xx/5xxPassthrough error from YouTube API

Troubleshooting: API Key Issues

  1. Check that the MATON_API_KEY environment variable is set:
echo $MATON_API_KEY
  1. Verify the API key is valid by listing connections:
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Troubleshooting: Invalid App Name

  1. Ensure your URL path starts with youtube. For example:
  • Correct: https://gateway.maton.ai/youtube/youtube/v3/search
  • Incorrect: https://gateway.maton.ai/v3/search

Resources

平台分布

Local Agent

96.79%
按下载量换算135

安全审计

暂无安全审计结果可展示。

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills