skills.rest
iAziz786
iAziz786COMMUNITY
Explore all skills by this author →
Website𝕏@iAziz786GitHub

firecrawl

Searches, scrapes, and interacts with web pages via a local Firecrawl API.

3|Updated Jul 5, 2021
Search Tags:#cli#firecrawl#web#scrape#crawl#self-hosted
One-click install
npx skills add https://github.com/iAziz786/dotfiles --skill firecrawl-iaziz786
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/iAziz786/dotfiles/tree/main/.agents/skills/firecrawl-cli
Command: npx skills add https://github.com/iAziz786/dotfiles --skill firecrawl-iaziz786

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Firecrawl solves the challenge of performing real-time web search, scraping, and interactive content retrieval using a self-hosted CLI, eliminating reliance on external APIs and enabling privacy-preserving workflows.

Core Features & Use Cases

  • Search the web for pages, sources, and references from a local Firecrawl instance.
  • Scrape and interact with pages that require navigation, clicks, or login, returning clean markdown suitable for LLMs.
  • Map and crawl large site sections to extract bulk content or targeted data while keeping results local.

Quick Start

Install the Firecrawl CLI and run a quick local scrape to verify the setup.

Frequently Asked Questions about firecrawl

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

FAQPage Schema
How do I scrape dynamic web pages and return clean markdown using a self-hosted instance?▼

You can scrape dynamic web pages by running the scrape command against your self-hosted Firecrawl instance, which navigates sites and returns clean markdown suitable for LLMs. Results are written locally to a .firecrawl directory.

Can I interact with web pages that require clicks or login before scraping content?▼

Yes, you can interact with pages requiring navigation, clicks, or login using the interact command. The self-hosted Firecrawl CLI handles these interactions and extracts live content from the URLs safely.

What is the best way to extract bulk content from large sections of a website locally?▼

The best way to extract bulk content is by using the map and crawl commands against your local Firecrawl API. This allows you to extract targeted data from large site sections while keeping all results local.

Does web scraping and crawling with this approach require an external API key?▼

No, web scraping and crawling with this self-hosted Firecrawl CLI does not require an external API key. It eliminates reliance on external APIs by running entirely against your own local Firecrawl instance.

How does local web search work when finding sources and references for privacy-preserving workflows?▼

Local web search works by querying your running local Firecrawl instance to find pages, sources, and references. This enables privacy-preserving workflows by keeping the search and retrieval process entirely local.

Are there limitations when handling safe output for extracted live content from URLs?▼

The Firecrawl CLI applies safe output handling for extracted live content and writes results to a local .firecrawl directory. It requires a running local Firecrawl API instance to execute search, scrape, map, crawl, and interact commands.

Related Skills

Explore More Software Engineering Skills→
iAziz786iAziz786
3

firecrawl-search

Search via self-hosted Firecrawl and extract full-page content from results.

Community
Intermediate
shynlee04shynlee04

web-search

Search the web and extract content via Tavily and Exa using the inference.sh CLI.

Community
Intermediate
az9713az9713
2

grinde-mapper

Generate GRINDE mind maps connecting concepts across chunks.

Community
Advanced
nathanvalenathanvale
2

firecrawl

Fetch web content and extract structured data via the Firecrawl API.

Community
Advanced