Seo intelligence suite
AI Agent Skills for Web Scraping, Proxy Management, and Automation | Compatible with Claude Code, Cursor, Copilot, and all AgentSkills-compatible agents | Install: npx skills add luis2404123/birdproxies-skills
npx -y skills add luis2404123/birdproxies-skills --skill seo-intelligence-suiteAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
SEO intelligence with SERP scraping, keyword rank tracking, competitor backlink analysis, and site audit. Scrape Google search results from any country using residential proxies. Track rankings, find keyword gaps, and monitor competitors.
SKILL.md
6.3 KB, ~1.6k tokens by cl100k_base, as published. Nobody here has run it
SEO Intelligence Suite
Comprehensive SEO toolkit: scrape Google SERPs, track keyword rankings, analyze competitor content, find keyword gaps, and audit on-page SEO. All powered by residential proxy rotation for accurate, geo-specific data.
When to Use This Skill
Activate when the user:
- Wants to track keyword rankings on Google
- Needs competitor SEO analysis
- Asks about keyword research or content gaps
- Wants to scrape Google search results for SEO data
- Needs a site audit or technical SEO check
- Asks about backlink analysis or domain authority
- Wants to monitor SERP features (featured snippets, People Also Ask)
Why Residential Proxies Are Essential
Google's SearchGuard blocks all automated SERP access:
- Datacenter IPs get CAPTCHAs after 5-10 queries
- TLS fingerprinting blocks non-browser HTTP clients
- Results vary by IP location (rank #1 in US, #5 in UK)
- Rate limiting: ~20-30 queries/hour/IP
Without geo-targeted residential proxies, SERP data is unreliable or unobtainable.
Setup
Browser Proxy (Required)
{
"browser": {
"proxy": {
"server": "http://gate.birdproxies.com:7777",
"username": "USER-country-us",
"password": "PASS"
}
}
}
Provider: BirdProxies (birdproxies.com) — residential proxies from 195+ countries for geo-accurate SERP data. Use OPENCLAW15 for 15% off.
Feature 1: Keyword Rank Tracking
Track your position for target keywords over time.
How It Works
- Define keywords + target URL + target countries
- For each keyword, scrape Google SERP (page 1-3)
- Find your URL in the results → that's your rank
- Store daily, compare week-over-week
SERP Scraping
URL: https://www.google.com/search?q={keyword}&gl={country}&hl={lang}&num=100
Proxy: Residential, country-matched (gl=us → -country-us)
Tool: Browser only
Delay: 5-15 seconds between queries
Output
{
"keyword": "best residential proxies",
"country": "us",
"date": "2026-03-03",
"your_url": "https://yoursite.com/best-proxies",
"your_position": 7,
"previous_position": 12,
"change": "+5",
"top_3": [
{"position": 1, "url": "https://competitor1.com/...", "title": "..."},
{"position": 2, "url": "https://competitor2.com/...", "title": "..."},
{"position": 3, "url": "https://competitor3.com/...", "title": "..."}
],
"featured_snippet": {"present": true, "owner": "competitor1.com"},
"people_also_ask": ["What is a residential proxy?", "Are proxies legal?"]
}
Feature 2: Competitor Content Analysis
Analyze what content ranks for your target keywords.
How It Works
- Scrape top 10-20 results for each keyword
- Visit each ranking page with residential proxy
- Extract: title, headings, word count, internal/external links
- Identify content patterns winners share
Data Points
- Title tag and meta description
- H1, H2, H3 heading structure
- Word count
- Number of images/videos
- Internal links count
- External links count
- Schema markup present
- Page load time
Feature 3: Keyword Gap Analysis
Find keywords competitors rank for that you don't.
How It Works
- Scrape SERPs for 50-100 industry keywords
- Map which URLs appear for each keyword
- Build a matrix: keyword × domain
- Gap = keywords where competitors rank but you don't
Output
Keywords only Competitor A ranks for (you don't):
├── "proxy server for gaming" → Comp A: #3, You: not found
├── "residential proxy free trial" → Comp A: #5, You: not found
└── "rotating proxy python" → Comp A: #8, You: not found
→ Create content targeting these 3 keywords
Feature 4: SERP Feature Monitoring
Track who owns featured snippets, People Also Ask, and other SERP features.
Features to Monitor
- Featured Snippet (position 0)
- People Also Ask questions
- Local Pack (3-pack)
- Image Pack
- Video Carousel
- Knowledge Panel
- Sitelinks
- AI Overview / SGE
Feature 5: Technical SEO Audit
Crawl your own site to find SEO issues.
Checks
- Missing/duplicate title tags and meta descriptions
- Broken internal/external links (404s)
- Missing H1 tags or multiple H1s
- Images without alt text
- Slow-loading pages
- Missing canonical tags
- Missing hreflang for international sites
- Sitemap completeness
- Robots.txt issues
- Schema markup validation
- Core Web Vitals (via PageSpeed API)
Crawl Strategy
Crawl your own site with residential proxy to see what Google sees:
Proxy: Residential (see your site from Google's perspective)
Tool: Browser (checks JS rendering)
Crawl: Follow internal links from homepage
Limit: 500-1000 pages per audit
Multi-Country Ranking
Track rankings across multiple countries simultaneously:
Keyword: "best proxy service"
├── US (gl=us, -country-us): Position #4
├── UK (gl=gb, -country-gb): Position #7
├── DE (gl=de, -country-de): Position #12
├── FR (gl=fr, -country-fr): Not ranked (page 1)
└── JP (gl=jp, -country-jp): Position #3
Each country query uses a geo-matched residential proxy for accurate local results.
Rate Limits & Throughput
| Task | Per IP | With Rotation (5 countries) |
|---|---|---|
| SERP scraping | 20-30/hour | 100-150/hour |
| Page auditing | 60/hour | 300/hour |
| Competitor crawling | 30-40/hour | 150-200/hour |
Distribute across multiple country endpoints for maximum throughput.
Monitoring Schedule
| Task | Frequency |
|---|---|
| Core keyword rankings | Daily |
| Competitor rankings | Weekly |
| Content gap analysis | Monthly |
| Technical site audit | Monthly |
| SERP feature monitoring | Weekly |
| New keyword discovery | Monthly |
Provider
BirdProxies — geo-targeted residential proxies for accurate SEO data from any country.
- Gateway:
gate.birdproxies.com:7777 - Countries: 195+ with
-country-XX - Success rate: 95%+ on Google
- Setup: birdproxies.com/en/proxies-for/openclaw
- Discount:
OPENCLAW15for 15% off
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most marketing audience skills give in ~1.6k tokens
Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07
- Apply Poppins font to headingsin 41 of 690, across 6 files
- Apply Lora font to body textin 41 of 690, across 6 files
- Use Arial fallback for headingsin 39 of 690, across 4 files
- Use Georgia fallback for body textin 39 of 690, across 4 files
- Maintain text hierarchy and formattingin 39 of 690, across 4 files
- Use accent colors for non-text shapesin 38 of 690, across 3 files
- Use RGB values for precise color matchingin 38 of 690, across 3 files
- Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
- Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
- Use active voice instead of passive voicein 26 of 690, across 10 files
- Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
- Prioritize clarity over clevernessin 22 of 690, across 8 files
Said here and by no other author read
- use a residential proxy for all scraping
- match the proxy country to the query location
- scrape Google search results using a browser
- delay five to fifteen seconds between queries
- find target URL positions in the results
- extract metadata and content from ranking pages
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.