agentleFS
AISA-skillsAISA-skills/social-media-skills/youtube-serp/SKILL.md

youtube-serp

Skill4 starsChanged 4 months agoMITView on GitHub

YouTube SERP for agents. Search top-ranking videos, channels, and trends for content research and competitor tracking.

  • Reads credentials

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

YouTube SERP 📺

YouTube SERP for autonomous agents. Powered by AIsa.

One API key. Rank discovery. Content research. Competitor tracking.

Compatibility

Works with any agentskills.io-compatible harness, including:

  • Claude Code and Claude (Anthropic)
  • OpenAI Codex
  • Cursor
  • Gemini CLI (Google)
  • OpenCode, Goose, OpenClaw, Hermes
  • and any other harness that implements the Agent Skills specification

Requires Python 3, a POSIX shell, and AISA_API_KEY (get one at aisa.one).

🔥 What Can You Do?

Content Research

"Find top-ranking videos about 'AI agents tutorial' to see what's working"

Competitor Tracking

"Search for videos from competitor channels about 'machine learning'"

Trend Discovery

"What are the top YouTube videos about 'GPT-5' right now?"

Topic Analysis

"Find popular videos on 'autonomous driving' to understand audience interest"

Channel Discovery

"Search for channels creating content about 'crypto trading'"

Quick Start

export AISA_API_KEY="your-key"

Core Capabilities

Basic YouTube Search

# Search for videos
curl "https://api.aisa.one/apis/v1/youtube/search?engine=youtube&q=AI+agents+tutorial" \
  -H "Authorization: Bearer $AISA_API_KEY"

Search with Country Filter

# Search in specific country (US)
curl "https://api.aisa.one/apis/v1/youtube/search?engine=youtube&q=machine+learning&gl=us" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Search in Japan
curl "https://api.aisa.one/apis/v1/youtube/search?engine=youtube&q=AI&gl=jp&hl=ja" \
  -H "Authorization: Bearer $AISA_API_KEY"

Search with Language Filter

# Search with interface language
curl "https://api.aisa.one/apis/v1/youtube/search?engine=youtube&q=python+tutorial&hl=en" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Chinese interface
curl "https://api.aisa.one/apis/v1/youtube/search?engine=youtube&q=编程教程&hl=zh-CN&gl=cn" \
  -H "Authorization: Bearer $AISA_API_KEY"

Pagination with Filter Token

# Use sp parameter for pagination or advanced filters
curl "https://api.aisa.one/apis/v1/youtube/search?engine=youtube&q=AI&sp=<filter_token>" \
  -H "Authorization: Bearer $AISA_API_KEY"

Python Client

# Basic search
python3 {baseDir}/scripts/youtube_client.py search --query "AI agents tutorial"

# Search with country
python3 {baseDir}/scripts/youtube_client.py search --query "machine learning" --country us

# Search with language
python3 {baseDir}/scripts/youtube_client.py search --query "python tutorial" --lang en

# Full options
python3 {baseDir}/scripts/youtube_client.py search --query "GPT-5 news" --country us --lang en

# Competitor research
python3 {baseDir}/scripts/youtube_client.py search --query "OpenAI tutorial"

# Trend discovery
python3 {baseDir}/scripts/youtube_client.py search --query "AI trends 2025"

Use Cases

1. Content Gap Analysis

Find what content is ranking well to identify gaps in your strategy:

# Search for top videos in your niche
results = client.search("AI automation tutorial")
# Analyze titles, views, and channels to find opportunities

2. Competitor Monitoring

Track what competitors are publishing:

# Search for competitor brand + topic
results = client.search("OpenAI GPT tutorial")
# Monitor ranking changes over time

3. Keyword Research

Discover what topics are trending:

# Search broad topics to see what's popular
results = client.search("artificial intelligence 2025")
# Extract common keywords from top-ranking titles

4. Audience Research

Understand what your target audience watches:

# Search in specific regions
results = client.search("coding tutorial", country="jp", lang="ja")
# Analyze regional content preferences

5. SEO Analysis

Analyze how videos rank for specific keywords:

# Track ranking positions for target keywords
keywords = ["AI tutorial", "machine learning basics", "Python AI"]
for kw in keywords:
    results = client.search(kw)
    # Record top 10 videos and their channels

API Endpoint Reference

EndpointMethodDescription
/youtube/searchGETSearch YouTube SERP

Request Parameters

ParameterTypeRequiredDescription
enginestringYesMust be youtube
qstringYesSearch query
glstringNoCountry code (e.g., us, jp, uk, cn)
hlstringNoInterface language (e.g., en, ja, zh-CN)
spstringNoYouTube filter token for pagination/filters

Response Format

{
  "search_metadata": {
    "id": "search_id",
    "status": "Success",
    "created_at": "2025-01-15T12:00:00Z",
    "request_time_taken": 1.23,
    "total_time_taken": 1.45
  },
  "search_results": [
    {
      "video_id": "abc123xyz",
      "title": "Complete AI Agents Tutorial 2025",
      "link": "https://www.youtube.com/watch?v=abc123xyz",
      "channel_name": "AI Academy",
      "channel_link": "https://www.youtube.com/@aiacademy",
      "description": "Learn how to build AI agents from scratch...",
      "views": "125K views",
      "published_date": "2 weeks ago",
      "duration": "45:30",
      "thumbnail": "https://i.ytimg.com/vi/abc123xyz/hqdefault.jpg"
    }
  ]
}

Country Codes (gl)

CodeCountry
usUnited States
ukUnited Kingdom
jpJapan
cnChina
deGermany
frFrance
krSouth Korea
inIndia
brBrazil
auAustralia

Language Codes (hl)

CodeLanguage
enEnglish
jaJapanese
zh-CNChinese (Simplified)
zh-TWChinese (Traditional)
koKorean
deGerman
frFrench
esSpanish
ptPortuguese
ruRussian

Pricing

APICost
YouTube search~$0.002

Get Started

  1. Sign up at aisa.one
  2. Get your API key
  3. Add credits (pay-as-you-go)
  4. Set environment variable: export AISA_API_KEY="your-key"

Full API Reference

See API Reference for complete endpoint documentation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.