Web, Search & Scraping Agent Skills

CRITICAL: Use for ferris-search installation and configuration.

Fetch and normalize any content source into clean text with metadata — YouTube video transcripts, TikTok captions, web articles, PDFs…

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

Complete browser automation with Playwright.

Collect real financial data for any US publicly traded company from free public sources (yfinance).

Find and download ebooks from Z-Library and Anna's Archive.

Debug hard-to-diagnose Firecrawl issues with systematic isolation and

Automate web crawling and data extraction with Firecrawl -- scrape pages, crawl sites, extract structured data, batch scrape URLs, and map…

Diagnose and fix Firecrawl common errors and API response codes.

Execute Firecrawl secondary workflow: LLM extraction, batch scraping,

Process, validate, and store Firecrawl scraped content with deduplication

Download an entire website as local files — markdown, screenshots, or multiple formats per page.

Full-site crawling, scraping, and site mapping via Firecrawl MCP.

Extract a URL's content as clean markdown, including JS-rendered pages.

Execute Firecrawl incident response procedures with triage, mitigation,

Install and configure Firecrawl SDK authentication for web scraping.

Drive a live browser on a scraped page: click, fill forms, log in, paginate, infinite-scroll.

Identify and avoid Firecrawl anti-patterns and common integration mistakes.

Implement Firecrawl scraping policy enforcement: domain blocklists,

Implement Firecrawl webhook event handling for async crawl and batch

CRAI's Stage 01 firm discovery, running natively as a claude.ai skill (no Vercel app required).