Web Scraping & Data Collection Claudeスキル

Ebook Text Extractor

Extracts clean, plain text from EPUB, MOBI, and PDF files for analysis and data processing.

YouTube Video to Audio

Downloads and converts YouTube videos into high-quality audio files using yt-dlp and ffmpeg.

Exa Semantic Web Search

Empowers Claude with semantic, neural search capabilities and specialized web filtering using the Exa API.

Blockchain Data Pipeline Validation

Validates blockchain data collection pipelines using a systematic 5-step empirical workflow to ensure data integrity and storage efficiency.

Brave Search Integration

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

Wget URL Reader

Fetches and downloads content from any URL using the powerful wget command-line utility.

Article Extractor

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

GitHub Harvester

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

Zhipu AI Search

Performs intelligent web searches via the Zhipu search engine with automated relative date resolution.

AI Tech Digest

Curates specialized AI technology news and technical insights using targeted search strategies and quality filtering rules.

Actress Classifier Development Guide

Streamlines the development of Python-based video classification systems with optimized scraping and incremental database management.

Web Search

Performs structured web searches via DuckDuckGo to retrieve real-time documentation, library information, and technical solutions.

Web Crawler & Search Indexer

Crawls entire websites and builds searchable full-text indexes of content converted into Markdown format.

Iterative Fact Verification

Ensures rigorous factual accuracy through systematic, multi-pass evidence validation and source tiering.

Tavily Web Search

Conducts real-time, AI-optimized web searches and content extraction to provide up-to-date information beyond Claude's knowledge cutoff.

Document Processor

Processes, analyzes, and transforms various file formats into structured data or new document types using a standardized CLI.

Video Metadata Parser & Downloader

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

Rip Video

Extracts audio, subtitles, and cover images from MP4 video files using MCP services and ffmpeg.

Crawl4AI Web Scraper

Converts complex web pages into clean, LLM-friendly markdown for seamless data extraction and processing.

Web Scraping & Content Extraction Tools

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

Video Downloader

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

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.

YouTube Transcript Downloader

Downloads and processes YouTube video transcripts in bulk from CSV files or individual URLs into structured Markdown format.

Web Researcher

Conducts deep, multi-source web research and synthesis without cluttering the primary conversation context.

Twitter Thread Extractor

Extracts and converts Twitter/X threads into clean, well-formatted markdown files using automated browser interaction.

Web Search & Summarizer

Performs focused web searches to retrieve and summarize real-time information from authoritative sources.

Daily Competition Scout

Automates the entire end-to-end competition management workflow from discovery and analysis to entry drafting and notification.

Advanced Research Assistant

Conducts exhaustive, discovery-driven research using parallel LLM agents and multi-source synthesis to deliver cited, high-confidence reports.

Article Extractor

Extracts clean, readable text from URLs by stripping away ads, navigation menus, and web clutter.