skills.rest
nhattran998
nhattran998COMMUNITY
Explore all skills by this author →
WebsiteGitHub

scrape

Extracts web page data into JSON using browser primitives and a codified skill.

Updated Mar 30, 2026
Search Tags:#automation#json#web#data-extraction#scrape
One-click install
npx skills add https://github.com/nhattran998/personal-athlete-agent --skill scrape-nhattran998
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/nhattran998/personal-athlete-agent/tree/main/.agents/skills/gstack-scrape
Command: npx skills add https://github.com/nhattran998/personal-athlete-agent --skill scrape-nhattran998

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pull data from a web page and return structured JSON by prototyping flows with browser primitives. The first call on a new intent creates a quick prototype, while subsequent calls route to a codified browser-skill for consistent, fast results.

Core Features & Use Cases

  • Prototype flows on new intents using $B primitives to generate JSON.
  • Route to a codified browser-skill for stable responses in ~200ms.
  • Read-only by default; for mutating actions (forms, clicks, submissions), use /automate.

Quick Start

Point the skill at a target web page to extract data and receive a JSON payload immediately.

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 web page and get JSON?▼

To extract data from a web page and return JSON, point the skill at a target URL to receive a structured JSON payload immediately. It prototypes extraction flows using browser primitives to pull data fast.

How does web data extraction handle repeated requests for the same intent?▼

Web data extraction handles repeated requests by routing subsequent calls to a codified browser-skill after prototyping the new intent. This ensures consistent extraction and delivers fast results in around 200ms.

Can I use web scraping for form submissions and clicks?▼

Web scraping is read-only by default, so you cannot use it directly for form submissions or clicks. For mutating actions on web pages, you need to use the /automate command instead.

What is the best way to automate data extraction from web pages?▼

The best way to automate data extraction is using a two-path flow that prototypes new intents with browser primitives first, then routes to a codified browser-skill. This approach delivers stable JSON extraction results in about 200ms.

When do I need to use /automate instead of standard web scraping?▼

You need to use /automate instead of standard web scraping whenever you want to perform mutating actions on a web page, such as filling out forms, clicking buttons, or submitting data. Standard scraping remains read-only.

Related Skills

Explore More Software Engineering Skills→
zhu637882-stackzhu637882-stack

scrape

Extract structured data from web pages into JSON payloads.

Community
Intermediate
datheredathere
3.7k

csv-wrangling

Automate CSV data wrangling workflows with qsv for indexing, profiling, transforming, and exporting.

Official
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