Web Scraping & Data Collection Agent Skills

Estonia Government Public Data Access

Accesses and queries over 130 Estonian official public data sources including business registries, land records, and national statistics.

Estonia Government Data Access

Accesses and queries 133 official Estonian public data sources including business, land, and legal registers.

Video Downloader

Downloads high-quality video and audio content from YouTube and other platforms for offline viewing and content archival.

Exa Semantic Search

Empowers Claude with neural web search capabilities to find high-quality information through semantic understanding rather than simple keyword matching.

MQL5 Article Extractor

Extracts and organizes technical trading documentation and articles from mql5.com for research and training data collection.

Web Research Agent

Conducts systematic web searches with source evaluation and hypothesis tracking to synthesize high-quality external information.

Article Extractor

Extracts clean, readable content from web articles and blog posts directly into Markdown format by removing clutter and ads.

Context Engineering Framework

Extracts and transforms unstructured information from various sources into structured, AI-interpretable formats.

You.com Claude Agent SDK Integration

Integrates Anthropic's Claude Agent SDK with You.com's HTTP MCP server to provide real-time web search and content extraction capabilities.

PDF Processing Toolkit

Facilitates comprehensive PDF manipulation, including data extraction, document generation, and form handling using Python and CLI tools.

Web to Markdown & Summarizer

Converts web pages into clean, LLM-friendly Markdown and provides customizable summarization levels directly within Claude Code.

Team Shinchan Research Agent

Conducts deep web research and extracts structured documentation using specialized librarian subagents.

LinkedIn Video Downloader

Downloads high-quality MP4 videos from public LinkedIn posts directly to your local directory without authentication.

Context Engineering Framework

Automates the extraction, structuring, and organization of unstructured data into AI-ready formats from web and local sources.

Jina Web Reader & Search

Extracts clean, LLM-friendly content from URLs and performs AI-powered web searches using the Jina AI Reader API.

Defuddle Web Content Extractor

Extracts clean, distraction-free Markdown content from web pages to optimize AI token usage and analysis.

WeChat Article Fetcher

Converts WeChat Public Account articles into clean Markdown using Playwright-based browser automation.

Gourmet Research Assistant

Conducts multi-source, evidence-based restaurant research with standardized scoring and auditable city guides.

Brave Search API

Performs real-time web and local searches using the Brave Search API directly via curl commands to retrieve current information and technical solutions.

Web Search Patterns

Optimizes online research by applying structured query patterns and advanced search techniques for precise information retrieval.

YouTube Transcript Downloader

Fetches and processes YouTube video transcripts, subtitles, and captions using automated tools and AI transcription.

Video Downloader

Downloads videos and audio from YouTube and other platforms for offline viewing, archival, and content repurposing.

Article Content Extractor

Extracts clean, readable text from blog posts and articles by removing ads, navigation, and clutter.

Web Investigation & Debugging

Analyzes website structures and debugs web scraping issues using Chrome DevTools to improve data extraction accuracy.

Article Extractor

Extracts clean, distraction-free text content from web URLs and saves it as readable text files.

YouTube Transcript Downloader

Extracts and converts YouTube video transcripts into clean, readable text files directly within the terminal.

Video Downloader

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

Firecrawl API

Extracts clean web content, crawls entire domains, and searches the web directly through the Firecrawl API using terminal commands.

Perplexity Research

Integrates the Perplexity API to conduct deep web research, capture real-time data, and generate structured reports with verifiable citations.

YouTube to Markdown (Lite)

Converts YouTube videos into structured Markdown research documents including transcripts, summaries, and comment insights.