Web Scraping & Data Collection Agent Skills

ClinicalTrials.gov Database

Accesses and queries the ClinicalTrials.gov API v2 to retrieve detailed medical study data, recruitment status, and eligibility criteria for clinical research.

Article Extractor

Extracts clean, readable text from web URLs by removing advertisements, navigation menus, and distractions.

BioRxiv Database

Searches and retrieves life sciences preprints from the bioRxiv server using keywords, authors, date ranges, and categories.

Extract Moves From Video

Extracts text commands, terminal inputs, and gameplay moves from screen recordings using optimized OCR and image preprocessing techniques.

Extract Moves from Video

Extracts typed commands and sequential text inputs from screen recordings and terminal sessions using optimized OCR workflows.

Video Downloader

Downloads videos and audio from YouTube and other streaming platforms with customizable quality and format options.

Code From Image

Extracts and implements code or algorithms from images by utilizing OCR tools, image preprocessing, and systematic verification strategies.

Modao Prototype Capture

Automates the extraction of Modao prototype pages, screenshots, and annotations into organized Markdown documentation.

Financial Document Processor

Extracts structured data from financial documents using OCR and text extraction while enforcing rigorous data safety and verification protocols.

Financial Document Processor

Automates the classification and extraction of data from financial documents while ensuring data integrity through rigorous safety and verification protocols.

YouTube Video Downloader

Downloads YouTube videos and extracts MP3 audio using optimized quality presets for social sharing and local storage.

Research Archival & GitHub Integration

Automates scraping, markdown archival, and GitHub Issue creation for AI research conversations and web content.

App Store Scraper

Scrapes and analyzes iOS and macOS App Store data using iTunes APIs to retrieve structured JSON for apps, reviews, and ratings.

Parallel Data Enrichment

Enriches lists and CSV files with web-sourced data like contact info, company funding, and executive details.

Parallel Deep Research

Conducts exhaustive, multi-step web investigations and generates comprehensive reports for complex research topics.

Parallel Web Content Extraction

Extracts high-fidelity, verbatim content from URLs, PDFs, and JavaScript-heavy sites using a token-efficient forked context.

Social Media Content Extractor

Extracts and organizes content from Threads and Instagram into structured Markdown for knowledge management tools like Obsidian and Notion.

Parallel Web Search

Conducts fast, cost-effective web research and information lookups with automated inline citations and structured data output.

Unified Browser Abstraction

Provides a unified interface for web scraping and content extraction across Playwright, Hyperbrowser, and Antigravity native providers.

Exa Search CLI

Enables real-time web searching and high-quality programming context retrieval using the Exa neural search engine.

Anysite Market Research

Conducts deep market analysis and competitive intelligence by aggregating data from Y Combinator, SEC filings, and social media platforms.

Competitor Intelligence Analysis

Gathers comprehensive competitive intelligence across LinkedIn, social media, and the web to track market movements and hiring trends.

Anysite CLI Data Extraction & Pipelines

Automates web data extraction, multi-source dataset pipelines, and LLM-powered data analysis through a unified command-line interface.

Competitor Intelligence & Analysis

Conducts deep-dive competitive research across web, social media, and professional networks to generate actionable market intelligence.

Person Intelligence Analyzer

Conducts deep multi-platform background research to generate comprehensive professional intelligence reports and outreach strategies.

YouTube Video Downloader

Downloads YouTube videos and extracts audio with optimized quality presets for easy sharing and local playback.

Universal Search & Data Retrieval

Executes autonomous search missions across local codebases and the web to return structured, attributed data.

Incremental API Fetching

Builds resilient, state-aware data ingestion pipelines for paginated APIs using advanced watermark tracking.

Incremental API Fetcher

Builds resilient data ingestion pipelines that handle paginated API results with state tracking and historical backfills.

Web Search Fallback Agent

Ensures uninterrupted research capabilities by delegating web searches to autonomous agents when primary search APIs fail or hit limits.