skills.rest
CerisonAutomation
CerisonAutomationCOMMUNITY
Explore all skills by this author →
GitHub

firecrawl

Scrape and crawl websites into clean Markdown for research.

Updated Aug 23, 2026
Search Tags:#firecrawl#web research#web scraping#URL mapping#website crawl#markdown extraction#documentation ingestion
One-click install
npx skills add https://github.com/CerisonAutomation/clud --skill firecrawl-cerisonautomation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/CerisonAutomation/clud/tree/main/assistant/src/config/bundled-skills/firecrawl
Command: npx skills add https://github.com/CerisonAutomation/clud --skill firecrawl-cerisonautomation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Firecrawl helps you turn messy web pages into clean, LLM-ready content so you can research, ingest, and analyze information without manually copying and cleaning HTML.

Core Features & Use Cases

  • Scrape any URL to clean Markdown: Extract a single page’s main content as readable Markdown (optionally including links).
  • Crawl entire sites recursively: Index documentation, blogs, and knowledge bases by following internal links and returning combined Markdown.
  • Search with page-level content: Retrieve full page text for top results (not just titles/snippets) for stronger web research.
  • Map site structure: Discover and list URLs without fetching full content first to plan a crawl/scrape strategy.

Quick Start

Use Firecrawl to scrape a specific documentation page URL and return its clean Markdown.

Frequently Asked Questions about firecrawl

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract web page content into clean Markdown for research?▼

Web scraping into clean Markdown extracts a single page's main content as readable text, removing HTML noise to prepare information for downstream research and content ingestion.

What is the best way to crawl an entire documentation site recursively?▼

Crawling entire sites recursively indexes documentation by following internal links and returning combined Markdown, allowing you to ingest multi-page knowledge bases without manual copying.

Can I discover site URLs before scraping to plan my crawl strategy?▼

Yes. Mapping site structure discovers and lists URLs without fetching full content first, enabling you to plan a crawl or scrape strategy before extracting page text.

Do I need an API key to scrape websites into Markdown?▼

Yes, website scraping requires Firecrawl configuration, specifically providing a cloud API key or a local server URL to authenticate and access tool-driven endpoints.

Can I run a web search that returns full page text instead of snippets?▼

Yes, web search with page-level content retrieves the full page text for top results rather than just titles or snippets, providing stronger context for web research.

Does web scraping work with dynamically loaded content on multi-page sites?▼

Web scraping handles multi-page sites by following internal links and extracting main content as Markdown, with optional limits and crawl parameters to control the scope of ingestion.

Related Skills

Explore More Education & Research Skills→
shekerkammashekerkamma

pp-firecrawl

Automate web scraping and crawling operations through the Firecrawl API.

Community
Advanced
malue-aimalue-ai
36

raglite

Index local PDF, Markdown, and plain text documents into structured Markdown for semantic search.

Official
Intermediate
roach88roach88
2

scraping-websites

Crawl static and JavaScript-rendered websites and extract structured data.

Community
Intermediate
juricamigac-from-hrjuricamigac-from-hr

scrape-webpage

Scrape webpage content, metadata, and images into migration-ready JSON and assets.

Official
Advanced