skills.rest
tony30552001
tony30552001COMMUNITY
Explore all skills by this author →
GitHub

scrape

Extract structured data from web pages via browser primitives and return JSON.

Updated Dec 26, 2025
Search Tags:#data extraction#browser automation#web data#scrape#intents#gstack
One-click install
npx skills add https://github.com/tony30552001/Genpic-master --skill scrape-tony30552001
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/tony30552001/Genpic-master/tree/main/.agents/skills/gstack/scrape
Command: npx skills add https://github.com/tony30552001/Genpic-master --skill scrape-tony30552001

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pulls data from web pages by prototyping flows with browser primitives, enabling quick data-path experiments without building full automation.

Core Features & Use Cases

  • Prototype data extraction flows: Quickly sketch how to gather text, metadata, and structured data from diverse web pages.
  • Intent-driven routing: When a new user intent emerges, prototype the data path and steer results toward a codified browser-skill for subsequent calls.
  • Non-mutative by default: Read-only extraction is emphasized; for mutations (forms, clicks), use the automate path.

Quick Start

Scrape a target page URL to extract and return structured data.

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 any web page without building full browser automation?▼

You can extract structured data by prototyping data flows with browser primitives to gather text and metadata without building full automation. The Skill identifies and extracts data from web pages and returns structured JSON output.

How does intent-driven routing work for prototyping web data extraction?▼

Intent-driven routing applies new intents to prototype the data path and steers results toward a codified browser-skill for subsequent calls. This allows you to test data extraction flows before committing to a fixed automation route.

Can I perform form submissions or click actions while scraping web data?▼

Web data scraping is non-mutative by default, emphasizing read-only extraction of text and metadata. For mutations such as form submissions or clicks, you must route operations through the automate path to ensure safe changes.

What format does the extracted web data return?▼

Extracted web data returns as structured JSON output. The Skill operates via Bash, Read, and AskUserQuestion primitives to identify and extract data from web pages, delivering results in a JSON format for prototyping data flows.

When should I use a prototype data extraction flow instead of a codified browser automation skill?▼

Use a prototype data extraction flow when you need to quickly sketch how to gather text, metadata, and structured data from diverse web pages. It allows rapid data-path experiments before routing to a codified browser-skill for subsequent calls.

Related Skills

Explore More Data & Analytics Skills→
mbastakismbastakis
5

crawl4ai

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

Community
Intermediate
xotongxotong

scrape

Extracts structured data from web pages and returns it as JSON.

Community
Intermediate
TwoTonedTwoToned

scrape

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

Official
Advanced
MonichreMonichre

open-researcher

Gather credible open-source research sources with ranked summaries and citations.

Community
Basic