[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75EZWDSQ70BVQ758K2AXGMC":3,"skill-same:01M75EZWDSQ70BVQ758K2AXGMC":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M75EZWDSQ70BVQ758K2AXGMC","smart_scraper",null,"Intelligent web scraping with automatic retry, rate limiting, and anti-detection via Firecrawl patterns.","LongLeo287\u002FSEOSONA-OS","LongLeo287","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F141803367?v=4","01M6JK75C62VCNZKR5BRZ386YV","LongLeo","01M75CK60XQGYJY3YDGGFJQDYT",2,"MIT","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fdata_engineering\u002Fsmart_scraper\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: \"smart_scraper\"\ndescription: \"Intelligent web scraping with automatic retry, rate limiting, and anti-detection via Firecrawl patterns.\"\nversion: \"1.0.0\"\ntags: [\"scraping\", \"data-extraction\", \"firecrawl\", \"web-scraping\", \"automation\"]\nconnector: \"scripts\u002Fconnectors\u002Fscraper_agent.py\"\n---\n\n# Skill: Smart Scraper\n\n## Execution Steps\n1. Accept target URL(s) and data extraction schema (what fields to extract).\n2. Analyze target: static HTML vs JS-rendered vs API-backed.\n3. Select strategy: Simple HTTP for static, Firecrawl\u002FPlaywright for dynamic.\n4. Execute with guardrails: rate limiting, rotating user agents, retry with backoff.\n5. Extract and validate data against schema.\n6. Output: Clean CSV\u002FJSON with extracted data.\n\n## Scraping Strategies\n| Target Type | Tool | Method |\n|---|---|---|\n| Static HTML | HTTP + BeautifulSoup | Direct parse |\n| JS-rendered SPA | Firecrawl \u002F Playwright | Headless browser |\n| Paginated lists | HTTP + pagination logic | Follow next links |\n| API-backed | Direct API calls | REST\u002FGraphQL |\n\n## Quality Validation\n- [ ] robots.txt respected\n- [ ] Rate limiting applied (max 1 req\u002Fsecond default)\n- [ ] Extracted data matches schema (no missing fields)\n- [ ] No PII inadvertently captured\n","# Skill: Smart Scraper\n\n## Execution Steps\n1. Accept target URL(s) and data extraction schema (what fields to extract).\n2. Analyze target: static HTML vs JS-rendered vs API-backed.\n3. Select strategy: Simple HTTP for static, Firecrawl\u002FPlaywright for dynamic.\n4. Execute with guardrails: rate limiting, rotating user agents, retry with backoff.\n5. Extract and validate data against schema.\n6. Output: Clean CSV\u002FJSON with extracted data.\n\n## Scraping Strategies\n| Target Type | Tool | Method |\n|---|---|---|\n| Static HTML | HTTP + BeautifulSoup | Direct parse |\n| JS-rendered SPA | Firecrawl \u002F Playwright | Headless browser |\n| Paginated lists | HTTP + pagination logic | Follow next links |\n| API-backed | Direct API calls | REST\u002FGraphQL |\n\n## Quality Validation\n- [ ] robots.txt respected\n- [ ] Rate limiting applied (max 1 req\u002Fsecond default)\n- [ ] Extracted data matches schema (no missing fields)\n- [ ] No PII inadvertently captured\n",{"name":5,"tags":24,"version":30,"connector":31,"description":7},[25,26,27,28,29],"scraping","data-extraction","firecrawl","web-scraping","automation","1.0.0","scripts\u002Fconnectors\u002Fscraper_agent.py","main","4fd50b1281e8cd978866b6b4556242605cabf708","2_KNOWLEDGE\u002Fskills\u002Fdata_engineering\u002Fsmart_scraper",1,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS","https:\u002F\u002Fseosona-os.vercel.app","https:\u002F\u002Fgithub.com\u002FLongLeo287","https:\u002F\u002Fwww.facebook.com\u002FResourceRookie2023","2026-10-09 15:14:13",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add LongLeo287\u002FSEOSONA-OS --skill smart_scraper",{"tool":47,"command":48},"bunx","bunx skills add LongLeo287\u002FSEOSONA-OS --skill smart_scraper",{"tool":50,"command":51},"pnpm","pnpm dlx skills add LongLeo287\u002FSEOSONA-OS --skill smart_scraper","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fdata_engineering\u002Fsmart_scraper\u002FSKILL.md",true,[],[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M75F0T3V3W7JQQ05X26NNN2T","web_crawler_katana","High-speed web crawling using Katana patterns for deep site mapping, URL discovery, and content extraction.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fweb_crawler_katana\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M75F0Q2QJXDGAFKC7D84GT88","server_log_analyzer","Analyzes Nginx\u002FApache server logs to identify Googlebot crawl patterns, errors, and performance bottlenecks.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fserver_log_analyzer\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M75F0KZP6D8R8XPN2YT35BAJ","schema_markup_generator","Auto-generates JSON-LD structured data for any page type (Article, Product, FAQ, LocalBusiness, etc.).","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fschema_markup_generator\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M75F0G3KX4Y86AXJXTKXVEVA","internal_linking_optimizer","Analyzes and optimizes the internal link graph of a website for SEO authority distribution.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Finternal_linking_optimizer\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M75F0CS1RYX4YPJC7N6RAAQJ","google_trends_analyzer","Detects trending topics and seasonal patterns using Google Trends data for content planning and keyword strategy.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fgoogle_trends_analyzer\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M75F0ASMQ1GKPFX82D19SRTN","brand_context_analyzer","Tracks brand mentions, sentiment, and online reputation across web sources.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fbrand_context_analyzer\u002FSKILL.md",[],[]]