Web Scraping & Data Collection Claudeスキル

Firecrawl Automation

Automates deep web crawling, structured data extraction, and website mapping directly within the Claude Code terminal.

Zenrows Automation

Automates advanced web scraping and anti-bot bypass tasks using the Zenrows toolkit via Rube MCP.

Agenty Workflow Automation

Automates web scraping, data extraction, and Agenty cloud operations directly within Claude via the Rube MCP integration.

Linkup Search Automation

Automates web search and data retrieval tasks by integrating the Linkup toolkit via Composio's Rube MCP.

Diffbot Automation

Automates Diffbot operations via Rube MCP to extract structured data from the web and manage knowledge graphs.

SerpApi Automation

Automates search engine data extraction and SerpApi operations through the Rube MCP framework.

Supadata Automation

Automates Supadata operations and data extraction tasks using Composio’s Rube MCP for seamless AI workflows.

Tavily Search Automation

Automates advanced web searches and real-time data retrieval using Tavily via the Rube MCP and Composio toolkit.

Web Content Fetcher

Extracts clean, readable text and titles from web pages without the overhead of browser automation.

PDF Processing

Extract data, manipulate documents, and programmatically generate PDF files using specialized libraries and tools.

Defuddle Web Content Extractor

Extracts clean, distraction-free Markdown content from web pages to optimize token usage and context window efficiency.

Google Places Search

Searches the Google Places API for business details, location reviews, and geographic coordinates directly from the command line.

Video Downloader

Downloads high-quality videos and audio from YouTube and other platforms for offline viewing, editing, or archival.

Competitive Ads Extractor

Extracts and analyzes competitor advertising strategies across platforms to provide actionable messaging and creative insights.

Comprehensive Research Agent

Ensures high-fidelity web research through structured source validation, error recovery protocols, and transparent reasoning cycles.

Web Research

Orchestrates a structured, multi-agent workflow to conduct deep-dive research, synthesize information from multiple sources, and generate comprehensive reports.

Personal Site & Blog Search

Searches personal websites, blogs, and portfolios to find individual expert perspectives and independent technical analysis.

People Research & Discovery

Conducts deep professional background research and identifies experts using advanced Exa search capabilities.

Company Intelligence & Research

Performs comprehensive company research, competitor analysis, and market intelligence using advanced Exa search capabilities.

Financial Report Advanced Search

Retrieves and analyzes SEC filings, earnings reports, and annual financial documents using high-precision advanced web search.

Advanced X (Twitter) Search

Searches and extracts real-time discussions, product announcements, and developer sentiment from X (Twitter) using advanced Exa search capabilities.

Firecrawl Web Scraper

Scrapes web content and extracts structured data from any URL or search query using the Firecrawl MCP.

URL to Markdown Converter

Converts any live webpage into clean, structured Markdown format using Chrome CDP for full JavaScript rendering.

X to Markdown Converter

Converts X (Twitter) tweets, threads, and articles into clean Markdown files with YAML front matter.

YouTube Video Downloader

Downloads YouTube videos and audio files with customizable quality settings and format options directly within Claude Code.

Competitive Ads Extractor

Extracts and analyzes competitor advertisements from major ad libraries to provide actionable insights for messaging and creative strategy.

USPTO Patent & Trademark Database

Accesses USPTO APIs to perform comprehensive patent and trademark searches, retrieve examination histories, and analyze intellectual property data.

ClinicalTrials.gov Database Skill

Accesses the ClinicalTrials.gov API v2 to search, filter, and export clinical study data for medical research and patient matching.

PubMed Database Explorer

Automates biomedical literature searches and programmatic data extraction from the PubMed database using E-utilities and advanced MeSH queries.

Perplexity Search

Performs AI-powered web searches with real-time information and source citations to access data beyond the model's knowledge cutoff.