skills.rest
mi179
mi179COMMUNITY
Explore all skills by this author →
WebsiteGitHub

scrape

Extract web page data into structured JSON via browser primitives.

1|Updated May 27, 2026
Search Tags:#automation#json#browser#web#data-extraction#scrape
One-click install
npx skills add https://github.com/mi179/claude-skills --skill scrape-mi179
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/mi179/claude-skills/tree/main/user/gstack/scrape
Command: npx skills add https://github.com/mi179/claude-skills --skill scrape-mi179

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pull data from a web page and return it as structured JSON, enabling automated extraction and reuse.

Core Features & Use Cases

  • Prototype data collection flows on first call using browser primitives and output JSON.
  • Route subsequent calls to a codified browser-skill for faster, deterministic results.
  • Read-only by default; for mutations (form fills, clicks) use the /automate path.

Quick Start

Call the scrape skill with a target URL to receive a JSON representation of the page data.

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 and return it as structured JSON?▼

Extract web data into structured JSON by calling the skill with a target URL. It prototypes the data collection flow on the first call using browser primitives and routes subsequent calls to a codified browser-skill for faster, deterministic results.

How does browser automation handle subsequent web scraping calls for consistency?▼

Browser automation handles subsequent web scraping calls by routing them to a codified browser-skill. This ensures faster and more deterministic results after the initial call prototypes the data extraction flow using basic browser primitives.

Can I perform mutations like form fills and clicks during web data extraction?▼

Web data extraction is read-only by default, so you cannot perform mutations like form fills and clicks during standard scraping. To execute mutations on a web page, you must use the designated /automate path instead.

What's the best way to automate data extraction from web pages for reuse?▼

Automate data extraction from web pages for reuse by calling the skill with a target URL to receive a JSON representation of the page data. This enables automated extraction and downstream reuse of the structured information.

Do I need any dependencies to pull data from a web page into JSON?▼

You do not need any external dependencies to pull data from a web page into JSON. The skill operates autonomously using built-in browser primitives to prototype the extraction flow and output the structured data.

Related Skills

Explore More Software Engineering Skills→
tony30552001tony30552001

scrape

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

Community
Advanced
Blake-JohnBlake-John

pymupdf

Convert PDF documents into Markdown, JSON, and text for LLM workflows.

Community
Intermediate
TwoTonedTwoToned

scrape

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

Official
Advanced
zhu637882-stackzhu637882-stack

scrape

Extract structured data from web pages into JSON payloads.

Community
Intermediate