Web Scraping & Data Collection Claude 技能

YouTube Transcript Extractor

Extracts and cleans transcripts from YouTube videos for quick reading and summarization.

IPO Tracker & TradingView Watchlist Generator

Tracks recent Initial Public Offerings and generates ready-to-import TradingView watchlists with enriched market data.

YouTube Video Downloader

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

Competitive Teardown & Strategy

Conducts deep-dive competitive intelligence by synthesizing pricing data, app reviews, job postings, and SEO signals into actionable product strategy insights.

Firecrawl Scraper

Extracts deep web content, screenshots, and parsed PDF data using the Firecrawl API.

Exa Web Search & Content Extraction

Searches the live web and extracts structured content or code examples using Exa AI's neural search engine.

Firecrawl Web Scraper

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

BrightData Scraper

Implements a progressive four-tier scraping strategy to retrieve content from any URL while bypassing bot detection and CAPTCHAs.

Bright Data Advanced Scraper

Executes a progressive four-tier scraping strategy to reliably extract content from websites while bypassing bot detection and CAPTCHAs.

Bright Data Scraper

Automates multi-tier web scraping with an intelligent fallback strategy to bypass bot detection and capture content from any URL.

Exa Semantic Search

Performs high-precision semantic search and structured research using the Exa neural search engine.

Exa Search

Performs semantic web research and content discovery using the Exa API to find contextually relevant information.

Tavily Web Search

Integrates real-time web search and content extraction capabilities into Claude Code using the Tavily API.

Tavily Web Search & Research

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

YouTube Transcript Downloader

Downloads, cleans, and polishes YouTube video transcripts and captions into structured markdown files.

Brave Web Search & Extraction

Performs headless web searches and extracts clean markdown content using the Brave Search API without requiring a browser.

YouTube Video Downloader

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

Advanced Video Downloader & Transcriber

Downloads and transcribes videos from 1000+ platforms into high-quality media files and searchable Markdown text.

Web Search & Documentation Agent

Optimizes technical information retrieval by delegating web searches to a specialized agent for structured, high-reliability results.

Web API Reverse Engineering

Reverse engineers web applications to discover hidden APIs and automatically generate comprehensive OpenAPI 3.1 specifications.

YouTube Transcript Extractor

Extracts text transcripts and captions from YouTube videos for analysis, summarization, and offline content processing.

PDF to Markdown Converter

Converts complex PDF documents into clean, structured Markdown while preserving tables, formatting, and images for AI context.

YouTube Transcript Analyzer

Extracts and analyzes YouTube video transcripts to provide summaries and answer specific questions about video content.

Indeed Germany Job Scraper

Automates the extraction of real-time job listings from Indeed Germany with advanced filtering and deep-dive capabilities.

Job Filtering & Lead Deduplication

Filters, deduplicates, and scores job listings to isolate high-quality technical roles from direct employers.

PySpider Task Manager

Automates web scraping task creation and management across social media, e-commerce, and SEO platforms via Feishu API integration.

Markdown Web Fetcher

Extracts clean, optimized markdown from URLs by stripping HTML bloat to maximize context window efficiency.

News Summary & AI Insight

Automates multi-source news gathering and generates interactive HTML dashboards with on-demand AI deep-dive analysis.

Scrape.do Web Scraper

Extracts content from websites using the Scrape.do API to bypass anti-bot protections and render dynamic JavaScript.

Web to Markdown

Converts web pages into clean Markdown files for local documentation storage and AI context.