pinchtab

Name: pinchtab
Availability: InStock
Author: mxyhi

Control Chrome via a local HTTP API for web automation and scraping.

467|42|Updated Feb 2, 2026

Search Tags:#browser automation #web testing #web scraping #chrome #headless #http api

Ready to run

npx skills add https://github.com/mxyhi/ok-skills --skill pinchtab

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pinchtab
Source: https://github.com/mxyhi/ok-skills/tree/main/pinchtab
Command: npx skills add https://github.com/mxyhi/ok-skills --skill pinchtab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates browser interactions, enabling AI agents to navigate websites, fill forms, extract data, and take screenshots without manual intervention.

Core Features & Use Cases

Browser Automation: Control Chrome via an HTTP API for tasks like navigation, clicking, and typing.
Web Scraping: Extract accessibility trees and readable text content from web pages.
Screenshots & PDFs: Capture screenshots and generate PDF versions of web pages.
Use Case: An AI agent can use Pinchtab to log into a web application, fill out a complex form, and then download a generated report as a PDF.

Quick Start

Use the pinchtab skill to navigate to https://example.com and take a screenshot.

Frequently Asked Questions about pinchtab

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

FAQPage Schema

How do I automate Chrome browser interactions for an AI agent workflow?▼

You can automate Chrome browser interactions by using a local HTTP API designed for AI agent workflows. This API facilitates web automation tasks such as navigation, element interaction via accessibility refs, and form filling without manual intervention.

Can I extract readable text and accessibility trees during web scraping?▼

Yes, web scraping is supported through the extraction of accessibility trees and readable text content from web pages. This allows an AI agent to process page content efficiently after navigating to a target URL.

How do I capture screenshots and generate PDFs from web pages via an HTTP API?▼

You can capture screenshots and generate PDF versions of web pages by sending requests to the local HTTP API. This enables automated documentation and reporting directly from a controlled Chrome browser instance.

Does this browser automation approach require manual intervention for form filling?▼

No, this approach operates without manual intervention, allowing AI agents to fill out complex forms automatically. It controls a Chrome instance via an HTTP API with a focus on security and efficiency for agent workflows.

What is the best way to interact with page elements using accessibility refs?▼

The best way to interact with page elements is by utilizing accessibility refs provided by the local HTTP API. This mechanism enables precise clicking, typing, and navigation actions within a controlled Chrome environment.

Are there limitations when using a headless Chrome HTTP API for web automation?▼

While designed for security and efficiency, this web automation approach is limited to operations supported by the Chrome instance and its local HTTP API. It does not handle actions outside the browser environment or require external dependencies.