Discover Agent Skills for web scraping & data collection. Browse 17 skills for Claude, ChatGPT & Codex.
Identifies and prevents common Firecrawl integration mistakes to optimize credit usage and data extraction quality.
Facilitates multi-turn research sessions and structured report generation using the Perplexity API.
Extracts clean, clutter-free Markdown from web pages to optimize token usage and context relevance.
Implements robust rate limiting, exponential backoff, and idempotency patterns for resilient FireCrawl API interactions.
Integrates Exa's neural search API to perform semantic web queries and retrieve contextually relevant data for RAG pipelines.
Monitors Twitter/X for real-time AI news, trending tools, and developer insights using the Bird CLI.
Identifies and resolves common Firecrawl integration mistakes, anti-patterns, and resource management issues during code reviews.
Executes a structured, plan-driven implementation workflow that prioritizes context discovery and systematic validation for the kurly-crawler project.
Automates LinkedIn profile discovery and data extraction using optimized search queries and structured result parsing.
Automates LinkedIn job searching and generates ATS-optimized resumes with integrated skill gap analysis and interview preparation.
Accelerates data retrieval and web automation using a high-performance, headless browser replacement for Chrome.
Automates web scraping workflows to collect and analyze job postings from major Korean and international job boards.
Identifies and prevents common FireCrawl integration mistakes, anti-patterns, and excessive credit consumption during web scraping.
Automates web data collection and proxy management via Bright Data and Rube MCP.
Automates AI-powered web search and data retrieval using Exa's neural search engine via the Rube MCP.
Automates CAPTCHA solving and bypass workflows using 2Captcha via the Rube MCP integration.
Automates complex web scraping and data extraction tasks by integrating the Zyte API with Claude Code via the Rube MCP.
Automates Countdown API operations via Composio and Rube MCP to manage e-commerce data and retail workflows.
Automates complex web scraping and data extraction tasks using LLM-powered Scrapegraph AI tools via the Rube MCP.
Automates advanced neural search and data retrieval tasks using Metaphor (Exa.ai) via the Rube MCP and Composio toolkit.
Automates complex data fetching and information retrieval tasks through the Rube MCP and Composio toolkit.
Automate complex web scraping workflows and data extraction using Apify's library of Actors directly within Claude Code.
Automates complex Jigsawstack operations including web scraping, AI-powered data extraction, and content processing directly within Claude Code.
Automates complex web scraping and data extraction tasks using Scrapfly’s high-performance proxy and anti-bot capabilities via Rube MCP.
Automates document parsing and structured data extraction from emails and PDFs using Parseur and Rube MCP.
Downloads high-quality video and audio content from YouTube and other platforms for offline archival, research, and editing.
Builds fully automated, AI-powered data collection agents that scrape, enrich, and store public data for free.
Conducts high-precision neural searches for web content, code examples, and company intelligence using the Exa MCP server.
Empowers Claude with high-quality neural search capabilities to retrieve real-time web data, code context, and company intelligence.
Conducts multi-source web investigations to produce comprehensive, cited research reports with verifiable evidence.
Scroll for more results...