skills.rest
tgmarinho
tgmarinhoCOMMUNITY
Explore all skills by this author →
Website𝕏@tgmarinhoGitHub

scrape

Extract structured data from web pages via browser automation primitives.

Updated May 15, 2026
Search Tags:#data extraction#browser automation#json#web scraping#web data#intent caching
One-click install
npx skills add https://github.com/tgmarinho/canetaco --skill scrape-tgmarinho
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/tgmarinho/canetaco/tree/main/.claude/skills/scrape
Command: npx skills add https://github.com/tgmarinho/canetaco --skill scrape-tgmarinho

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually copying data from web pages is slow and error-prone, and writing a custom scraper for every site wastes engineering time. This Skill pulls data from a page on demand: the first request on a new intent prototypes the extraction flow through browser primitives and returns JSON, while repeat requests on a matching intent route to a codified browser skill and return in roughly 200ms. ## Core Features & Use Cases - Intent-based caching: First call on a new intent prototypes the flow; subsequent matching calls reuse the codified path for fast responses. - Structured JSON output: Returns extracted page data as JSON rather than raw HTML, ready for downstream processing. - Read-only safety: Restricted to data extraction; mutating flows like form fills, clicks, and submissions are delegated to the /automate skill instead. - Use Case: Ask "what's on this pricing page" or "extract the product listings from this URL" and receive structured JSON without writing a scraper. ## Quick Start Ask the assistant to scrape a specific URL and extract the data you need, for example: scrape this page and pull all product names and prices into JSON.

Frequently Asked Questions about scrape

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

FAQPage Schema
How do I scrape data from a web page without writing code?▼

Invoke the scrape skill with a URL and a description of the data you want, such as "scrape this page" or "extract prices from this URL". It prototypes the extraction flow through browser primitives and returns the result as JSON.

What is the difference between scrape and automate for browser tasks?▼

Scrape is read-only: it extracts data from pages and returns JSON. Automate handles mutating flows like form fills, button clicks, and submissions. If your task changes page state, use automate instead.

Why is the second scrape request on the same page much faster?▼

The first call on a new intent prototypes the extraction flow, which takes longer. Subsequent calls matching that intent route to a codified browser skill, returning results in roughly 200ms.

Can I use web scraping to fill out forms or click buttons?▼

No. This skill is explicitly read-only and does not perform clicks, form fills, or submissions. For those mutating browser interactions, the documentation directs you to the /automate skill.

What format does scraped web data come back in?▼

Extracted data is returned as JSON, making it directly usable for downstream processing, storage, or analysis without parsing raw HTML yourself.

Related Skills

Explore More Software Engineering Skills→
cegit27cegit27
3

setup-browser-cookies

Import authenticated Chromium session cookies into a headless browser session.

Official
Intermediate
KaranKathur06KaranKathur06

data-pipeline

Build scheduled ETL workflows that extract, transform, and load data into analytics destinations.

Community
Intermediate
whmathews15whmathews15
1

process-meetings

Process synced meeting notes into person pages, task records, and summaries.

Community
Advanced
TwoTonedTwoToned

scrape

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

Official
Advanced