How do I install the Ferret skill?

Run npx skillmds@latest add javimosch/ferret in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Ferret skill do?

Use this skill when the user wants to scrape web pages, extract data from websites, or perform web crawling tasks. It is listed under Coding & Dev Tools on SkillMD.

Is Ferret safe to use?

SkillMD's automated safety review verdict for this skill is PASS. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ferret?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ferret free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ferret?

javimosch (@javimosch) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ferret by javimosch — Agent Skill

Name: Ferret
Author: javimosch

File contents

ferret Plugin

Declarative web scraping tool. Extract data from websites using a query language. Supports scraping, crawling, and data extraction from web pages.

Commands

Web Scraping

ferret web scrape — Scrape data from websites

Utility

ferret _ _ — Passthrough to ferret CLI

Usage Examples

"Scrape this website"
"Extract data from web page"
"Crawl and scrape multiple pages"
"Query web page data"

Installation

brew install ferret

Or via Go:

go install github.com/MontFerret/ferret/cmd/ferret@latest

Examples

# Scrape with FQL script
ferret web scrape script.fql

# Output to file
ferret web scrape script.fql --output results.json

# CSV output format
ferret web scrape script.fql --format csv

# Headless mode
ferret web scrape script.fql --headless

# Set timeout
ferret web scrape script.fql --timeout 30

# Any ferret command with passthrough
ferret _ _ script.fql --output data.json
ferret _ _ --headless script.fql

Key Features

Declarative - FQL query language
Dynamic content - Headless Chrome support
Crawling - Multi-page crawling
Data extraction - Structured data output
JSON/CSV - Multiple output formats
JavaScript - Execute JavaScript on pages
Cross-platform - Linux, macOS, Windows
Fast - Efficient scraping
Flexible - Custom queries
Extensible - Plugin system

Notes

Uses FQL (Ferret Query Language)
Supports JavaScript execution
Can handle dynamic content
Perfect for data extraction
Works with single pages and crawling

Frequently asked questions

Ferret