skills.rest
TwoToned
TwoTonedOFFICIAL
Explore all skills by this author →
GitHub

scrape

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

Updated Mar 11, 2026
Search Tags:#automation#json#browser#web#data-extraction#scrape
One-click install
npx skills add https://github.com/TwoToned/gearflow --skill scrape-twotoned
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/TwoToned/gearflow/tree/main/.claude/skills/gstack/scrape
Command: npx skills add https://github.com/TwoToned/gearflow --skill scrape-twotoned

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pull data from web pages automatically, turning on-page content into structured data you can reuse in downstream workflows.

Core Features & Use Cases

  • Prototyping: on first invocation, the flow is prototyped using the gstack primitives and returns JSON.
  • Deterministic routing: subsequent calls route to a codified browser-skill and return results in ~200ms.
  • Read-only operation by default: mutations should use /automate, making it safe to run in planning and automation contexts.
  • Use cases include extracting headings, links, metadata, or table data from dynamic pages for dashboards and integrations.

Quick Start

Ask me to scrape a web page to return its data 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 data from a webpage into JSON?▼

To extract data from a webpage into JSON, request a scrape of the target URL. The system prototypes the extraction flow on the first call and returns structured JSON data from the page content.

Can I scrape dynamic web pages for headings and links?▼

Yes, you can scrape dynamic web pages to extract headings, links, metadata, or table data. The operation uses a browser-based skill to capture content from dynamic pages for downstream integrations.

Why does web scraping take longer on the first call?▼

Web scraping takes longer on the first call because the system prototypes the extraction flow using shell-like primitives. Subsequent matching calls route to a codified browser-skill, returning results in around 200ms.

Does web scraping support form fills and submissions?▼

No, web scraping is read-only and does not support form fills, clicks, or submissions. For mutating flows and interactions that change page state, you should use an automation tool instead.

What is the best way to automate data extraction for dashboards?▼

The best way to automate data extraction for dashboards is to use a scraping skill that converts on-page content into structured JSON. This allows you to directly feed the extracted data into your downstream workflows.

Related Skills

Explore More Data & Analytics Skills→
ivanrvpereiraivanrvpereira
17

crwl

Extract readable web page content and structured JSON data from URLs via the crwl CLI.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
velamints2velamints2

Agent Browser

Automates headless browser interactions via a command-line interface for AI agents.

Community
Advanced
mbastakismbastakis
5

crawl4ai

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

Community
Intermediate