skills.rest
aicodepro
aicodeproOFFICIAL
Explore all skills by this author →
GitHub

scrape

Extract data from web pages using browser automation primitives.

Updated Jun 22, 2026
Search Tags:#data extraction#browser automation#json#web scraping#read-only#gstack
One-click install
npx skills add https://github.com/aicodepro/ai-agent-nexi --skill scrape-aicodepro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/aicodepro/ai-agent-nexi/tree/main/agent/skills/gstack/scrape
Command: npx skills add https://github.com/aicodepro/ai-agent-nexi --skill scrape-aicodepro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually copying data from web pages is slow and error-prone. This Skill pulls structured data from a page on demand, prototyping the flow on first use and routing repeat requests to a fast codified browser-skill path. ## Core Features & Use Cases - Web Data Extraction: Pull data from any web page when asked to "scrape", "get data from", "pull", "extract from", or report "what's on" a page. - Adaptive Routing: First call on a new intent prototypes the flow via $B primitives and returns JSON; subsequent matching calls route to a codified browser-skill and return in roughly 200ms. - Read-Only Safety: Restricted to read-only extraction; mutating flows like form fills, clicks, and submissions are delegated to the /automate skill. - Use Case: Ask the assistant to pull the pricing table from a competitor's product page and receive the data back as structured JSON. ## Quick Start Ask the assistant to scrape the data from a specific web page URL and return it as 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 with gstack?▼

Invoke the scrape skill with a target URL and describe what to extract. The first call prototypes the flow using $B browser primitives and returns JSON; later calls on the same intent reuse a codified browser-skill for faster results.

What is the difference between scrape and automate in gstack?▼

Scrape is read-only: it extracts data from pages without changing anything. Automate handles mutating flows such as form fills, clicks, and submissions. Use scrape for extraction and /automate for interactions.

Can the scrape skill fill out forms or click buttons?▼

No. The scrape skill is explicitly read-only and does not perform clicks, form fills, or submissions. For any mutating browser flow, the skill directs you to use the /automate skill instead.

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

The first call on a new intent prototypes the extraction flow via $B primitives. Subsequent calls matching that intent route to a codified browser-skill, which returns results in roughly 200 milliseconds.

What are the limitations of read-only web scraping?▼

Read-only scraping cannot interact with pages behind login flows, multi-step wizards, or actions requiring state changes. Data dependent on user interaction must be reached through a mutating automation skill instead.

Related Skills

Explore More Software Engineering Skills→
brikkoAIbrikkoAI
1

tavily

Search the web with filters and extract markdown content from URLs.

Official
Intermediate
vctplatformvctplatform

data-engineer

Design and implement data pipelines and reporting for the VCT Platform.

Community
Advanced
metric-space-aimetric-space-ai
2

universal-scraping

Coordinate repeatable web data extraction workflows into durable, queryable artifacts.

Official
Advanced
sanskarbasnetsanskarbasnet
1

scrape

Extract page titles, descriptions, and links as JSON from URLs.

Community
Intermediate