LogoClawIndex
CasesSkillsAbout
LogoClawIndex

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.

Skills tagged: content extraction

Browse skills that share this tag.

  • xcrawl - Single URL extraction with XCrawl Scrape API
    web scrapingcontent extractionasync scrapingJSON extraction

    ★ 59 · Updated 2026-06-15

    Extract content from single URLs using XCrawl Scrape APIs with various output formats and JSON extraction options.

    ⚙ fetch single URL⚙ select output format⚙ execute sync request
  • pptx - PowerPoint Presentation Management
    presentationsofficepowerpointdocument processing

    ★ 45,849 · Updated 2026-05-28

    Create, read, edit, and validate PowerPoint presentations

    ⚙ read .pptx files⚙ extract text⚙ create presentations
  • openakita/skills@pptx - PPTX Presentation File Processor
    file processingdocument processingpresentationpptx

    ★ 1,986 · Updated 2026-05-28

    Process PowerPoint files including read, create, edit, and extract text content

    ⚙ read pptx file⚙ create slides⚙ edit presentation
  • web-search - Web search with real browser
    web searchcontent extractionbrowser automationscraping

    ★ 11 · Updated 2026-05-09

    Searches the web and extracts page content as markdown using a real browser to bypass bot detection.

    ⚙ search web⚙ extract page content⚙ download files
  • youtube-transcript-metadata - Fetch YouTube video transcript and metadata
    YouTubevideotranscriptmetadata

    ★ 0 · Updated 2026-03-24

    Fetch transcript text and video metadata from YouTube in parallel

    ⚙ fetch transcript⚙ extract metadata⚙ validate transcript
  • x402engine-web - Lightweight web scraping and screenshot service
    web scrapingscreenshotsearchcontent extraction

    ★ 1 · Updated 2026-03-20

    Provides lightweight web scraping and screenshots via x402engine through the Obul proxy

    ⚙ scrape URL to markdown⚙ capture screenshot⚙ search web
  • crawl - Browser-based content extraction for authenticated websites
    browser automationcontent extractionweb scrapingauthentication

    ★ 0 · Updated 2026-03-09

    Extract content from websites requiring login using authenticated browser sessions

    ⚙ open browser instance⚙ navigate pages⚙ click elements
  • crawl - Browser Automation for Login-Required Content Extraction
    web scrapingbrowser automationcontent extractionlogin-required websites

    ★ 602 · Updated 2026-03-09

    Use logged-in browsers with Chrome DevTools to extract content from login-required websites

    ⚙ Detect operating system environment⚙ Launch Chrome browser instances⚙ Verify Chrome DevTools MCP connection
  • web-to-markdown - Convert Web Pages to Clean Markdown
    web conversionmarkdownbrowser automationcontent extraction

    ★ 18 · Updated 2026-02-24

    Converts webpage URLs to clean Markdown using a locally installed browser

    ⚙ convert URLs to Markdown⚙ handle JS-rendered pages⚙ extract main content
  • web-to-markdown - Convert web pages to clean Markdown format
    web scrapingmarkdown conversionbrowser automationcontent extraction

    ★ 0 · Updated 2026-02-24

    Converts webpage URLs to clean Markdown using local web2md CLI

    ⚙ convert webpage to markdown⚙ extract main content⚙ handle JS-rendered pages
  • web-to-markdown - Convert Web Pages to Clean Markdown Format
    web scrapingmarkdown conversionbrowser automationcontent extraction

    ★ 7 · Updated 2026-02-24

    Converts webpage URLs to clean Markdown using local web2md CLI with Puppeteer and Readability

    ⚙ call local web2md CLI⚙ handle JS-rendered pages⚙ extract main content
  • url-content-loading - URL Content Extraction Tool for Multiple Platforms
    web scrapingcontent extractionsocial mediavideo processing

    ★ 211 · Updated 2026-02-13

    Extracts text and metadata from URLs across various platforms including social media, videos, and code repositories

    ⚙ load URLs⚙ extract text content⚙ extract metadata