Web Scraping & Data Collection Agent Skills

Competitive Ads Extractor

Extracts and analyzes competitor advertisements from ad libraries to uncover winning messaging, pain points, and creative strategies.

YouTube Transcript Extractor

Extracts and saves subtitles or transcripts from any YouTube video URL directly to your local workspace.

Firecrawl Web Scraper

Scrapes websites, searches the web, and extracts structured data from pages using the token-efficient Firecrawl API.

External Research Explorer

Conducts targeted external research for competitive analysis, technical standards, and API documentation to provide actionable project context.

Video Downloader

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

YouTube Transcript Downloader

Downloads and processes YouTube video transcripts, subtitles, and captions with automatic fallback to AI-powered transcription.

Pattern Radar Configurator

Configures sources, relevance weights, and domain interests for the Pattern Radar discovery tool.

Twscrape Twitter Data Collection

Extracts comprehensive data from Twitter/X using GraphQL APIs with robust account rotation and session management.

Web Browser & Scraper

Enables autonomous web scraping and content extraction using shot-scraper to interact with and retrieve data from websites.

Playwright Web Scraper

Implements production-proven Playwright web scraping patterns with a selector-first approach and robust error handling.

Article Extractor

Extracts clean, clutter-free content from web articles and blog posts for readable text storage.

USPTO Database Connector

Accesses comprehensive USPTO APIs for patent and trademark searches, examination history, and intellectual property analysis.

Perplexity Search for Claude

Enables Claude to perform AI-powered web searches with real-time information and source citations using Perplexity models.

AI Web Research

Conducts comprehensive, web-grounded research with automatic citations and structured data output directly from your terminal.

Web Crawler & URL Extractor

Crawls websites using the Tavily API to convert web pages into local markdown files for offline analysis and documentation retrieval.

Advanced Gemini Web Search

Enhances Claude Code with deep web searching capabilities using Gemini for complex information gathering and synthesis.

YouTube Transcript Downloader

Downloads and processes YouTube video transcripts, captions, and subtitles into clean text or VTT formats.

Article Content Extractor

Extracts clean, distraction-free text from web articles and blog posts for easy reading and archiving.

YouTube Video Downloader

Downloads YouTube videos with customizable resolution, format, and audio extraction options via yt-dlp.

Competitive Ads Extractor

Extracts and analyzes competitor advertising strategies from major ad libraries to optimize your own messaging and creative performance.

YouTube Transcript Analyzer

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

Scrapedo Web Scraper

Automates the extraction of structured data from websites using optimized scraping patterns.

YouTube Transcriber

Extracts and formats transcripts from YouTube videos, playlists, and channels using a single unified command.

FireCrawl

Crawls and scrapes websites to extract structured article content using the FireCrawl API.

Competitive Ads Extractor

Extracts and analyzes competitor advertisements from platforms like Facebook and LinkedIn to provide strategic messaging and creative insights.

YouTube Transcript Extractor

Extracts subtitles and transcripts from YouTube videos and saves them as local text files with timestamps.

Fetch Stores

Fetches business listings, store locations, and restaurant details from Google Maps using the Dumpling AI API.

RSS Feed Fetcher

Fetches and parses RSS feeds from multiple URLs to gather articles for content creation.

Pattern Radar Adapter Creator

Generates and tests custom data source adapters for the pattern-radar monitoring system.

Content Crawler

Extracts high-speed, read-only markdown content from documentation, blogs, and static websites.