Web Scraping & Data Collection Claude 스킬

FireCrawl SDK Patterns

Implements production-ready architectural patterns and best practices for FireCrawl SDK integrations in TypeScript and Python.

Structured Web Research

Orchestrates parallel subagents to conduct systematic, well-documented web research and synthesize findings into comprehensive reports.

YouTube Video Downloader

Downloads YouTube videos and audio with customizable quality and format settings directly through the command line.

Web Research & Synthesis

Conducts structured, multi-threaded web research by spawning specialized subagents to gather and synthesize information.

Web Scraping & Content Extraction Tools

Automates documentation collection and structured data extraction using Playwright, BeautifulSoup, and Scrapy templates.

API Scraper Architect

Provides standardized architectural patterns and Pydantic models for building robust API documentation scrapers.

Deep Research & Analysis

Conducts exhaustive, multi-threaded investigations using parallel agent teams to produce high-confidence synthesized reports from 20+ sources.

WASDE Data Ingestor

Automates the extraction and parsing of monthly USDA WASDE reports into standardized datasets for agricultural market analysis.

Video Downloader

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

Media Downloader

Downloads high-quality video and audio from over 1,000 platforms with automated metadata extraction and QR code support.

Unified Web Search

Performs simultaneous multi-engine searches using Gemini, Codex, and Claude to provide a consolidated, high-precision information report.

Firecrawl Scraper

Automates complex web data extraction, page crawling, and document parsing using the Firecrawl API.

Firecrawl Web Scraper

Extracts clean web content, captures screenshots, and parses PDFs using the powerful Firecrawl API.

Tavily Web Search

Empowers Claude with real-time web search, content extraction, and advanced crawling capabilities using the Tavily API.

Tavily Web Search

Empowers Claude with real-time web search, automated content extraction, and deep research capabilities using the Tavily API.

Tavily Web Search & Extraction

Provides real-time web search, content extraction, and automated site crawling capabilities powered by the Tavily API.

Obsidian Web Clipper Template Creator

Generates structured JSON templates for the Obsidian Web Clipper by analyzing web page metadata and verifying CSS selectors.

Web Research Pro

Verifies technical requirements and gathers real-time information through structured web searches and documentation analysis.

Video & Transcript Downloader

Downloads videos, audio, and clean paragraph-style transcripts from YouTube and other yt-dlp supported platforms.

YouTube & HLS Video Downloader

Downloads high-quality video and audio from YouTube and HLS streaming platforms like Vimeo and Mux using yt-dlp and ffmpeg.

Deep Research Orchestrator

Orchestrates multi-agent parallel workflows to perform comprehensive web research, data collection, and structured report generation.

Gemini Web Search

Enhances Claude with advanced web search capabilities using Gemini to retrieve and synthesize real-time information from the internet.

Blog Profile Analyzer

Analyzes blogs and online publications to extract deep insights into author perspectives, political leanings, and hidden biases.

Automated Video Parser & Downloader

Automates video metadata extraction and file downloading by processing task lists through MCP services.

RSS Feed Operations

Reads and processes RSS/Atom feeds from any blog URL with intelligent automatic feed discovery.

Rust Web Crawler

Extracts website content and structure at high speeds to generate LLM-ready Markdown, interactive site maps, and structured data for RAG pipelines.

GitHub Harvester

Extracts and processes comprehensive data from GitHub repositories for ingestion into RAG pipelines and LLM knowledge bases.

Gemini Web Search

Integrates Google Gemini's web search capabilities into Claude Code for comprehensive, real-time information retrieval.

Persistent Sector Caching

Optimizes yfinance data retrieval by implementing a permanent SQLite caching layer to bypass API rate limits and 401 errors.

Alpha Finder

Gathers real-time market intelligence from across the web and social media to inform prediction market trading decisions.