skills.rest
yashs33244
yashs33244COMMUNITY
Explore all skills by this author →
GitHub

scrape

Extract structured data from web pages and return it as JSON.

1|Updated May 5, 2026
Search Tags:#browser automation#scrape#web data extraction#intent routing#structured json#read-only retrieval#rapid extraction
One-click install
npx skills add https://github.com/yashs33244/my-mac-claude --skill scrape-yashs33244
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/yashs33244/my-mac-claude/tree/main/skills/gstack/scrape
Command: npx skills add https://github.com/yashs33244/my-mac-claude --skill scrape-yashs33244

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extracts the exact information you need from a web page without manual copy-paste, so you can turn “what’s on this page?” into structured JSON quickly and repeatedly.

Core Features & Use Cases

  • Intent-first flow prototyping: First call on a new intent designs the scraping flow and returns JSON immediately, establishing the extraction pattern for later runs.
  • Low-latency repeated extraction: Subsequent calls on a matching intent route to a codified browser skill and return results in about 200ms.
  • Read-only scraping safety: Designed for extraction and data pulling only; for mutating actions like form fills, clicks, or submissions, use the /automate flow instead.
  • When to use: Use it when asked to scrape, get data from, pull from, extract from, or identify what’s on a page, especially when you want machine-readable outputs.

Quick Start

Ask: “Scrape this page and return the product names, prices, and availability as JSON (for my page intent).”

Frequently Asked Questions about scrape

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

FAQPage Schema
How do I extract web data from a page and return it as structured JSON?▼

To extract web data as structured JSON, define a natural-language intent for the page. The scraping workflow prototypes the extraction flow on the first call and returns the requested data as machine-readable JSON immediately.

How does intent routing work for repeated web page scraping tasks?▼

Intent routing for repeated scraping works by codifying the browser flow during the first extraction. Subsequent calls matching that intent route directly to the established pattern, returning structured JSON data in about 200ms.

Can I use this to fill out forms or click buttons on a web page?▼

You cannot use this to fill out forms, click, or submit. It implements a read-only scraping workflow designed exclusively for pulling and extracting page data as JSON without performing any mutating browser actions.

What is the best way to pull product names and prices from a web page quickly?▼

The best way to pull product names and prices quickly is to ask for a scrape of the page returning those specific fields as JSON. This establishes an intent pattern that enables low-latency, repeated extraction for future runs.

Does read-only web data extraction require manual setup for each new page intent?▼

Read-only web data extraction requires manual setup only once per new intent. The initial call designs the scraping flow using $B primitives and immediately returns JSON, which is then reused automatically for matching intents.

Related Skills

Explore More Data & Analytics Skills→
eskoNBGeskoNBG
1

web-reader

Retrieve structured web page content and metadata from a URL.

Community
Advanced
profmikegreeneprofmikegreene
1

plan-ingestion

Parses pilot plans and hypotheses into structured JSON or tabular data for downstream analysis.

Community
Intermediate
TwoTonedTwoToned

scrape

Prototype web scraping flows with shell-like primitives and return JSON.

Official
Advanced
mbastakismbastakis
5

crawl4ai

Crawl web pages with Python and extract structured data as Markdown or JSON.

Community
Intermediate