skills.rest
diazMelgarejo
diazMelgarejoCOMMUNITY
Explore all skills by this author →
Website𝕏@Melgarejo_yDiazGitHub

firecrawl

Scrape, search, parse, and monitor web content via Firecrawl CLI, MCP, and REST API.

Updated Mar 22, 2026
Search Tags:#firecrawl#mcp#web scraping#rest api#document parsing#markdown extraction#page monitoring
One-click install
npx skills add https://github.com/diazMelgarejo/orama-system --skill firecrawl-diazmelgarejo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/diazMelgarejo/orama-system/tree/main/bin/orama-system/skills/firecrawl
Command: npx skills add https://github.com/diazMelgarejo/orama-system --skill firecrawl-diazmelgarejo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires firecrawl-cli, and includes references (resource) components.

What problem does it solve? Agents often need clean, structured content from URLs, local documents, or live web pages, but raw HTML extraction is brittle and interactive pages resist simple scraping. This Skill routes web extraction, document parsing, page monitoring, and research-index queries through Firecrawl's CLI, MCP tools, or REST API. ## Core Features & Use Cases - Web Extraction & Interaction: Scrape known URLs into clean markdown, interact with live pages requiring clicks, forms, or login, and crawl or map entire sites. - Document Parsing & Research: Convert local PDF, DOCX, XLSX, and other files to markdown, and search a scientific paper index plus GitHub issues, PRs, and READMEs. - Monitoring & Deliverables: Create recurring page-change monitors with webhook, email, or Slack notifications, and produce finished artifacts like research briefs, SEO audits, and lead lists via workflow skills. - Use Case: After a search tool surfaces a documentation URL, scrape it with --only-main-content to verify an API's exact field names, then set up a monitor to get notified when that page changes. ## Quick Start Ask the agent to scrape a known URL with Firecrawl and return the main content as clean markdown, authenticating the MCP session first if needed.

Frequently Asked Questions about firecrawl

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

FAQPage Schema
How do I scrape a URL into clean markdown with Firecrawl?▼

Run `firecrawl scrape "<url>" -f markdown --only-main-content` via the CLI, or call the `firecrawl_scrape` MCP tool after authenticating. The `--only-main-content` flag strips navigation, footers, and ads so the output is the actual page content.

When should I use Firecrawl versus a search engine for web research?▼

Firecrawl is an extraction tool, not a discovery tool. Use a search chain (EXA, Brave, Perplexity) first to find candidate URLs, then use Firecrawl to scrape, interact with, or monitor the specific pages that search surfaced.

Can Firecrawl parse local PDF and DOCX files?▼

Yes, `firecrawl parse ./report.pdf -o output.md` converts local PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, and HTML files to markdown, with options for AI summaries or question answering. Documents with public URLs should use `scrape` instead.

Does Firecrawl work without an API key?▼

A rate-limited keyless free tier supports search, scrape, interact, parse, and research-index endpoints through official clients (MCP, CLI, SDK). Crawl, map, monitor, extract, and batch endpoints still require an API key from a signed-up account.

How do I get notified when a web page changes?▼

Use `firecrawl monitor create` with a target URL and schedule (cron or natural language like "every 30 minutes"). It diffs each check against the last snapshot, filters noise with an AI goal judge, and notifies via webhook, email, or Slack.

Why is my Firecrawl job failing or returning unexpected output?▼

Run `firecrawl ask` with the failing jobId; the AI support agent diagnoses the issue from your team's job logs and account state and suggests corrected parameters. This command is CLI/REST-only with no MCP equivalent.

Related Skills

Explore More Software Engineering Skills→
polymerdaopolymerdao
1

polymer-pay-stableenrich-exa

Perform semantic web search and content extraction via StableEnrich through Polymer Pay.

Official
Advanced
CliffValeCliffVale
1

firecrawl-workflows

Orchestrates Firecrawl workflows that produce research reports, audits, and structured web-data deliverables.

Community
Intermediate
kortix-aikortix-ai
20.2k

search

Searches the web and scrapes pages to answer questions with cited sources.

Official
Intermediate
ricardojjuliaricardojjulia

firecrawl

Search, scrape, and monitor web pages through the Firecrawl CLI and REST API.

Community
Advanced