菜单
YouTube Data API integration with managed OAuth. Search videos, manage playlists, access channel data, and interact with comments. Use this skill when users want to interact with YouTube. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
A股量化选股扫描器，模型驱动自适应因子评分。通过 Tushare 扫描全 A 股 5000+ 只股票，检测市场环境（波动率、动量、资金面、板块轮动），动态调整因子权重，输出选股榜/异动榜/行业分布的 HTML 报告。适用于 A 股选股、量化筛选、因子分析、市场环境诊断、板块轮动、动量策略、价值投资筛选。Use for Chinese A-share stock screening, quantitative stock picking, sector rotation, market regime detection.
3-layer personality system for AI agents: Yuan (base persona), Ishiki (private self-awareness), Public Ishiki (external behavior rules). Give your agent a consistent character, emotional depth, and safe guest interaction boundaries. Use when: (1) Want agent to have a consistent personality, (2) Agent needs different behavior for owner vs strangers, (3) Building a personal AI companion, (4) Agent responses feel generic and robotic, (5) User says 'be more like...', 'act as...', or wants to customize agent character.
Auto-snapshot workspace before dangerous commands (rm -rf, git clean, git reset --hard). Zero-cost hardlink dedup on macOS/Linux, robocopy mirror on Windows. Use when: (1) About to run destructive file operations, (2) User asks to protect workspace files, (3) Before bulk delete/move operations, (4) User mentions fear of losing files. Also provides snapshot listing and one-command restore.
Click-to-zoom lightbox for chat images, screenshots, and generated visuals. Scroll-wheel zoom (0.5x–5x), drag-to-pan, pinch gesture on mobile, keyboard shortcuts. Zero dependencies — pure CSS + vanilla JS. Use when: (1) Chat contains images the user wants to inspect, (2) Browser screenshots need closer examination, (3) Generated images are too small in the chat bubble, (4) User says 'zoom in' or 'enlarge' about an image.
Persistent cross-session memory system with fact extraction, semantic search, and compiled memory layers. Your agent remembers everything across sessions — user preferences, project context, past decisions, personal details. Use when: (1) User references something from a previous conversation, (2) Agent needs project context it learned before, (3) User says 'remember this' or 'do you remember when...', (4) Starting a new session that should inherit past knowledge, (5) Agent keeps forgetting things between sessions.
Quantitative stock scanner with model-driven adaptive factor scoring. Scans ~100 US large/mid-cap stocks via Finnhub API, detects market regime (volatility, momentum, breadth), dynamically adjusts factor weights, and produces ranked selection/anomaly lists with HTML reports. Use for US stock screening, quantitative stock picking, factor analysis, market regime detection, stock scoring, building a model portfolio, or finding momentum/value/quality plays.
| name | youtube |
| description | YouTube Data API integration with managed OAuth. Search videos, manage playlists, access channel data, and interact with comments. Use this skill when users want to interact with YouTube. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). |
| compatibility | Requires network access and valid Maton API key |
| metadata | {"author":"maton","version":"1.0","clawdbot":{"emoji":"🧠","requires":{"env":["MATON_API_KEY"]}}} |
Access the YouTube Data API v3 with managed OAuth authentication. Search videos, manage playlists, access channel information, and interact with comments and subscriptions.
# 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
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.
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"
Manage your Google OAuth connections at https://ctrl.maton.ai.
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
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
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.
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
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.
GET /youtube/youtube/v3/search
Query parameters:
part - Required: snippetq - Search querytype - Filter by type: video, channel, playlistmaxResults - Results per page (1-50, default 5)order - Sort order: date, rating, relevance, title, viewCountpublishedAfter - Filter by publish date (RFC 3339)publishedBefore - Filter by publish date (RFC 3339)channelId - Filter by channelvideoDuration - short (<4min), medium (4-20min), long (>20min)pageToken - Pagination tokenExample:
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"
}
}
]
}
GET /youtube/youtube/v3/videos?part=snippet,statistics,contentDetails&id={videoId}
Parts available:
snippet - Title, description, thumbnails, channel infostatistics - View count, likes, commentscontentDetails - Duration, dimension, definitionstatus - Upload status, privacy statusplayer - Embedded player HTMLExample:
curl -s -X GET "https://gateway.maton.ai/youtube/youtube/v3/videos?part=snippet,statistics&id=dQw4w9WgXcQ" -H "Authorization: Bearer $MATON_API_KEY"
GET /youtube/youtube/v3/search?part=snippet&forMine=true&type=video&maxResults=25
POST /youtube/youtube/v3/videos/rate?id={videoId}&rating=like
Rating values: like, dislike, none
GET /youtube/youtube/v3/videos?part=snippet,statistics&chart=mostPopular®ionCode=US&maxResults=10
GET /youtube/youtube/v3/videoCategories?part=snippet®ionCode=US
GET /youtube/youtube/v3/channels?part=snippet,statistics,contentDetails&id={channelId}
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 /youtube/youtube/v3/channels?part=snippet,statistics&forUsername={username}
GET /youtube/youtube/v3/playlists?part=snippet,contentDetails&mine=true&maxResults=25
GET /youtube/youtube/v3/playlists?part=snippet,contentDetails&id={playlistId}
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
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 /youtube/youtube/v3/playlists?id={playlistId}
GET /youtube/youtube/v3/playlistItems?part=snippet,contentDetails&playlistId={playlistId}&maxResults=50
POST /youtube/youtube/v3/playlistItems?part=snippet
Content-Type: application/json
{
"snippet": {
"playlistId": "PLxyz123",
"resourceId": {
"kind": "youtube#video",
"videoId": "abc123xyz"
},
"position": 0
}
}
DELETE /youtube/youtube/v3/playlistItems?id={playlistItemId}
GET /youtube/youtube/v3/subscriptions?part=snippet&mine=true&maxResults=50
GET /youtube/youtube/v3/subscriptions?part=snippet&mine=true&forChannelId={channelId}
POST /youtube/youtube/v3/subscriptions?part=snippet
Content-Type: application/json
{
"snippet": {
"resourceId": {
"kind": "youtube#channel",
"channelId": "UCxyz123"
}
}
}
DELETE /youtube/youtube/v3/subscriptions?id={subscriptionId}
GET /youtube/youtube/v3/commentThreads?part=snippet,replies&videoId={videoId}&maxResults=100
POST /youtube/youtube/v3/commentThreads?part=snippet
Content-Type: application/json
{
"snippet": {
"videoId": "abc123xyz",
"topLevelComment": {
"snippet": {
"textOriginal": "Great video!"
}
}
}
}
POST /youtube/youtube/v3/comments?part=snippet
Content-Type: application/json
{
"snippet": {
"parentId": "comment123",
"textOriginal": "Thanks for your comment!"
}
}
DELETE /youtube/youtube/v3/comments?id={commentId}
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' }
})
}
);
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'}
}
)
dQw4w9WgXcQ)UC (e.g., UCxyz123)PL (user) or UU (uploads)pageToken for pagination through large result setspart parameter is required and determines what data is returnedcurl -g when URLs contain brackets (fields[], sort[], records[]) to disable glob parsingjq 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.| Status | Meaning |
|---|---|
| 400 | Missing YouTube connection or invalid request |
| 401 | Invalid or missing Maton API key |
| 403 | Forbidden - quota exceeded or insufficient permissions |
| 404 | Video, channel, or playlist not found |
| 429 | Rate limited (10 req/sec per account) |
| 4xx/5xx | Passthrough error from YouTube API |
MATON_API_KEY environment variable is set:echo $MATON_API_KEY
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
youtube. For example:https://gateway.maton.ai/youtube/youtube/v3/searchhttps://gateway.maton.ai/v3/search