skills.rest
shekerkamma
shekerkammaCOMMUNITY
Explore all skills by this author →
GitHub

pp-firecrawl

Automate web scraping and crawling operations through the Firecrawl API.

Updated May 22, 2026
Search Tags:#data extraction#firecrawl#web scraping#batch processing#deep research#crawling#url mapping
One-click install
npx skills add https://github.com/shekerkamma/peopletech-marketplace --skill pp-firecrawl-shekerkamma
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pp-firecrawl
Source: https://github.com/shekerkamma/peopletech-marketplace/tree/main/plugins/integrations/skills/firecrawl
Command: npx skills add https://github.com/shekerkamma/peopletech-marketplace --skill pp-firecrawl-shekerkamma

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the manual effort of interacting with the Firecrawl API for web scraping, crawling, and data extraction tasks. It provides a structured CLI interface that handles authentication, rate limiting, retries, and output formatting, so you can focus on the data you need rather than API plumbing.

Core Features & Use Cases

  • Web Scraping: Extract content from single URLs or batch-process multiple sites with options for ad-blocking, PDF parsing, and mobile emulation.
  • Crawling: Discover and crawl entire websites with depth control, sitemap handling, and path filtering.
  • Structured Extraction: Use LLMs to extract structured data from pages based on custom prompts.
  • Deep Research: Run automated deep research operations on queries with configurable depth and URL limits.
  • Agent-Optimized Output: JSON/compact modes, field selection, dry-run previews, and provenance tracking for AI agent consumption.

Quick Start

Use the pp-firecrawl skill to scrape https://example.com and return the extracted content as markdown.

Frequently Asked Questions about pp-firecrawl

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

FAQPage Schema
How do I automate web scraping and crawling without managing API authentication manually?▼

Automated web scraping and crawling is handled through a structured CLI interface that manages Firecrawl API authentication, rate limiting, and retries. You provide a bearer token to interact with the binary and receive formatted JSON or markdown output.

Can I extract structured data from web pages using a custom prompt?▼

Structured data extraction is supported by applying LLMs to web pages based on your custom prompts. The Skill processes the extracted content and returns structured formats, allowing you to isolate specific fields and parse targeted information from URLs.

Does batch crawling support depth control and path filtering for entire websites?▼

Batch crawling supports website discovery with configurable depth control, sitemap handling, and path filtering. You can target specific sections of a domain while utilizing local SQLite caching to store results and manage large-scale crawling operations.

What's the best way to preview extracted web data before processing a full crawl?▼

A dry-run preview mode allows you to inspect targeted web data before executing full crawling operations. The Skill generates preview outputs from the Firecrawl API request, enabling you to verify field selection and extraction parameters without consuming full API credits.

Why does deep research require configurable depth and URL limits?▼

Deep research operations require configurable depth and URL limits to control the scope of automated query processing and prevent excessive API consumption. These parameters bound the Firecrawl crawling radius, ensuring the research returns targeted provenance tracking within safe operational limits.

Do I need a bearer token to use the firecrawl-pp-cli binary for URL mapping?▼

A bearer token is required for firecrawl-pp-cli binary execution to authenticate URL mapping and web scraping requests. The Skill relies on this token to interface with the Firecrawl API, ensuring authorized access for data extraction and site discovery workflows.

Related Skills

Explore More Data & Analytics Skills→
shekerkammashekerkamma

pp-cal-com

Compose Cal.com v2 API sequences into single CLI commands.

Community
Advanced
Blake-JohnBlake-John

pymupdf

Convert PDF documents into Markdown, JSON, and text for LLM workflows.

Community
Intermediate
mkurmanmkurman
321

tavily

Perform live web search, extraction, mapping, and crawling via Tavily's REST API.

Community
Intermediate
appautomatonappautomaton
18

html-to-markdown

Converts HTML or live web pages into structured Markdown with metadata and link inventories.

Official
Intermediate