Web Scraping & Data Collection Claudeスキル

Systematic Info Gathering

Executes a structured four-phase framework for comprehensive technical and general-purpose research and data verification.

Professional People Search

Conducts real-time OSINT research to retrieve verified career timelines, professional backgrounds, and biographical data for individuals and entities.

Video Downloader

Downloads high-quality video and audio content from YouTube and other platforms directly through the Claude Code interface.

YouTube Video Downloader

Downloads YouTube videos and audio with customizable quality and format settings using yt-dlp.

Competitive Ads Extractor

Scrapes and analyzes competitor advertisements from major ad libraries to identify successful messaging, creative patterns, and market positioning.

YouTube Transcript Downloader

Extracts and converts YouTube transcripts or auto-generated captions into clean, readable text files.

Advanced Video Downloader

Downloads high-quality videos and extracts audio from over 1000 platforms including YouTube, Bilibili, and TikTok using yt-dlp.

Competitive Ads Extractor

Extracts and analyzes competitor advertisements from major ad libraries to uncover successful messaging patterns and creative strategies.

Firecrawl Real Estate Scraper

Extracts structured property data from real estate listing URLs using Firecrawl AI for market analysis and content creation.

X (Twitter) Data & Scraping

Extracts comprehensive X (Twitter) data, manages account monitoring, and performs bulk social media analytics via REST API and MCP.

JBK Investment Sentiment Tracker

Collects YouTube economic commentary and calculates the 'Honey Index' by comparing financial predictions with actual market performance.

Summarize & Transcribe

Summarizes and extracts content from URLs, YouTube videos, and local files using multiple AI model providers.

Web Research & Synthesis

Conducts structured, multi-threaded web research by delegating sub-tasks to specialized agents and synthesizing findings into comprehensive reports.

Wikidata Search & Authority Control

Searches the Wikidata knowledge base to retrieve structured entity details and universal external identifiers.

Structured Web Research

Conducts systematic web investigations by deploying parallel subagents to gather, verify, and synthesize information from multiple sources.

Web Research & Synthesis

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

Web Research & Synthesis

Conducts multi-threaded, deep-dive web investigations by orchestrating parallel subagents to gather and synthesize complex information.

Structured Web Research

Conducts systematic web research by planning subtasks, delegating to research agents, and synthesizing findings into comprehensive reports.

Website Crawler

Maps complex website structures and discovers URLs using a high-performance Go-powered engine with TypeScript integration.

Video Downloader

Automates video and audio downloads from various web platforms with customizable quality and format settings using yt-dlp.

YouTube Transcript Extractor

Extracts high-quality subtitles and transcripts from YouTube videos in multiple formats and languages for analysis and automation.

FireCrawl SDK Upgrade & Migration

Streamlines FireCrawl SDK upgrades by identifying breaking changes and automating version migrations across your codebase.

FireCrawl Quick Start

Bootstraps a minimal FireCrawl integration to verify API connectivity and client initialization.

Researcher

Gathers, synthesizes, and documents information from web sources and local codebases to provide evidence-based recommendations.

Defuddle Content Cleaner

Extracts clean, clutter-free markdown from web pages to optimize context window usage and reduce token consumption.

AI Research Collector

Aggregates and preprocesses high-quality AI programming tips and best practices from major developer platforms.

Victorian Tender Assessment & Pursuit

Automates Victorian government tender discovery, alignment scoring, and the generation of comprehensive pursuit packages.

Firecrawl Web Scraper

Converts websites into LLM-ready markdown and structured data for high-fidelity web research and automation.

PySpider Development Toolkit

Streamlines the creation of production-ready PySpider web crawlers using standardized templates, advanced scraping patterns, and enterprise-grade best practices.

DuckDuckGo Web Research & Search

Empowers Claude with deep web searching, real-time news aggregation, and automated information retrieval via DuckDuckGo.