Extracts structured data from web pages and returns it as JSON.
npx skills add https://github.com/xotong/claude-marketplace --skill scrape-xotong
Please help me install this Agent Skill. Skill: scrape Source: https://github.com/xotong/claude-marketplace/tree/main/plugins/gstack/skills/scrape Command: npx skills add https://github.com/xotong/claude-marketplace --skill scrape-xotong
Pull structured data from web pages and convert it into JSON for automation and integration tasks.
Invoke the scrape skill on a page to prototype data extraction and return JSON; subsequent calls reuse the codified browser-skill for speed.
High-intent search queries and answers about installing and using this skill.
Web page data extraction works by prototyping a flow on a new intent using browser-based cues and returning JSON. Subsequent calls on a matching intent route to a codified browser-skill to achieve consistent ~200ms responses.
Repeated web scraping requests are slow if they re-prototype the extraction flow every time. This tool routes subsequent calls on a matching intent to a codified browser-skill to achieve consistent ~200ms responses.
You cannot use this browser-based extraction tool to automate web form submissions because it is read-only by default. It is designed for non-mutating web exploration; for mutations, you must use the /automate flow.
The best way to pull structured data for automation tasks is to prototype the extraction flow on a new intent to return JSON. Subsequent calls then route to a codified browser-skill for fast, consistent ~200ms responses.
You do not need any external dependencies to scrape web pages into JSON. The tool operates independently using browser-based primitives to prototype the extraction flow and return structured JSON data.
tony30552001Extract structured data from web pages via browser primitives and return JSON.
mi179Extract web page data into structured JSON via browser primitives.
nhattran998Extracts web page data into JSON using browser primitives and a codified skill.
phanijappsAutomate web scraping and data extraction with the Lightpanda headless browser.
