Automate web scraping, searching, mapping, crawling, and extraction via mode-based JSON commands.
npx skills add https://github.com/CK991357/gemini-chat --skill firecrawl-ck991357
Please help me install this Agent Skill. Skill: firecrawl Source: https://github.com/CK991357/gemini-chat/tree/main/src/skills/firecrawl Command: npx skills add https://github.com/CK991357/gemini-chat --skill firecrawl-ck991357
Firecrawl automates web crawling and data extraction across websites, reducing manual scraping effort through a unified, mode-based tool that supports sync and async workflows.
Use the firecrawl tool to crawl a site or perform a targeted scrape, for example: {"mode": "scrape", "parameters": {"url": "https://example.com", "formats": ["markdown"]}}
High-intent search queries and answers about installing and using this skill.
To extract web data asynchronously, use the crawl or extract modes. These modes gather structured data across multiple pages automatically, reducing manual scraping effort for ongoing data pipelines.
The best way to scrape synchronously is using the scrape mode with a JSON command. You specify the target URL and desired data formats like markdown to retrieve instant results from the website.
Yes, you can retrieve sitemaps and perform site-wide data extraction. The map mode gathers structured data across pages, allowing you to build datasets for analytics like product price benchmarking.
Yes, you need a valid URL format to start web scraping. The tool validates URLs to ensure they begin with http:// or https:// before executing any data collection or extraction commands.
Mode-based JSON commands execute web data collection by specifying a mode like scrape or crawl, and a nested parameters object. This structure validates inputs and triggers synchronous or asynchronous tasks.
Synchronous modes like scrape, search, and map are designed for instant results rather than ongoing data pipelines. For site-wide extraction across numerous pages, asynchronous modes are required to avoid limitations.
yuma588Automate synchronous and asynchronous web crawling with nested parameters.
aws-samplesProcess and analyze CSV, JSON, and text data files with automated cleaning and transformation.
orthogonal-shExtracts structured data from web pages and URLs via modular scraping workflows.
vm0-aiRun Apify Actors and retrieve dataset items via API.
