web-scraping

Installation
SKILL.md

Scrape — General-Purpose Web Scraping & Data Extraction

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Scrape websites, extract structured data, and automate browser interactions. Pick the best API for the task — or combine several for comprehensive extraction.

1. Scrapegraph — AI-Powered Scraping with Natural Language

Installs
2
GitHub Stars
980
First Seen
Jun 3, 2026
web-scraping — athina-ai/goose-skills