scrape

Extract structured data from web pages into JSON using a read-only browse shim.

5|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/timurgaleev/vibestack --skill scrape-timurgaleev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/timurgaleev/vibestack/tree/main/skills/scrape
Command: npx skills add https://github.com/timurgaleev/vibestack --skill scrape-timurgaleev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables extracting structured data from web pages by using a read-only browse shim to navigate pages and capture data as JSON.

Core Features & Use Cases

  • Navigate pages and inspect content with the browse shim
  • Extract structured values into JSON for records or lists
  • Fall back to curl + HTML parsing for static pages when the shim is unavailable

Quick Start

Provide the target URL and the fields you want, and the skill will navigate the page, extract the data, and return it as JSON.

Frequently Asked Questions about scrape

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

FAQPage Schema
How do I extract structured data from a web page into JSON?

To extract structured data from a web page into JSON, you provide a target URL and the desired fields. The skill navigates the page using a read-only browse shim, maps the extracted values, and returns a JSON object or list.

Can I scrape dynamic web content or does it only work on static pages?

You can scrape dynamic web content when the browse shim is available. If the shim is unavailable, the skill falls back to using curl and HTML parsing to extract data from simple static pages.

How do I map specific HTML fields into a JSON object?

You map specific HTML fields into a JSON object by providing the target URL and defining the fields you want. The skill applies selectors to navigate the page content and outputs the extracted values into a structured JSON format.

What is the best way to scrape a list of records from a website?

The best way to scrape a list of records is to provide the target URL and specify the fields for each record. The skill navigates the pages and maps the extracted data into a structured JSON list.

Do I need any external dependencies to extract web data into JSON?

No external dependencies are required. The skill uses a built-in read-only browse shim to navigate pages and capture data, with a curl fallback for static HTML parsing when the shim is unavailable.

What happens if the browse shim is unavailable during web scraping?

If the browse shim is unavailable during web scraping, the skill falls back to using curl and HTML parsing to extract data. This ensures you can still process simple static pages and map the values to JSON.