pinchtab

Automate browser tasks via PinchTab CLI and HTTP API.

10.0k|752|Updated Feb 15, 2026
One-click install
npx skills add https://github.com/pinchtab/pinchtab --skill pinchtab-pinchtab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pinchtab
Source: https://github.com/pinchtab/pinchtab/tree/main/skills/pinchtab
Command: npx skills add https://github.com/pinchtab/pinchtab --skill pinchtab-pinchtab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

PinchTab provides automated browser control for AI agents, enabling tasks like navigating sites, inspecting elements, clicking flows, filling forms, and data extraction without manual scripting.

Core Features & Use Cases

  • Navigation and Control via CLI and HTTP API to drive a local Chrome instance.
  • Stable element refs and flexible selectors (e5, e12, CSS, XPath, text, semantic) for reliable automation.
  • Safety defaults and multi-profile workflow suitable for local deployment, profiling, and re-use across tasks.
  • Real-world use cases include form automation, data extraction, login flows, and multi-site tasks with persistent profiles.

Quick Start

Open PinchTab, navigate to a URL, and extract the page text.

Frequently Asked Questions about pinchtab

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

FAQPage Schema
How do I automate browser tasks for AI agents without manual scripting?

Automate browser tasks for AI agents by driving PinchTab to open pages, inspect elements, and interact with web apps through CLI or HTTP API workflows. It handles navigation, form filling, and data extraction without manual scripting.

What's the best way to fill forms and extract data using browser automation?

Fill forms and extract data by utilizing stable accessibility refs and flexible selectors like CSS, XPath, and text matching. These reliable automation selectors ensure consistent element targeting across multi-site tasks.

Do I need specific binaries to enable AI agents to control a local Chrome instance?

Yes, you need PinchTab binaries to enable AI agents to control a local Chrome instance. The system enforces safety defaults for local use and supports both local and remote server deployments.

Can I manage multiple browser profiles for persistent login automation?

Yes, you can manage multiple browser profiles for persistent login automation. The multi-profile workflow supports local deployment, profiling, and re-use across tasks while maintaining safety defaults.

Why does my web scraping automation fail when element selectors change?

Web scraping automation fails when selectors change because standard CSS selectors are brittle. PinchTab solves this by providing stable accessibility refs that maintain reliable element targeting.