browser-pilot

Automate browser navigation, form filling, and data extraction with session management.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/PedroPaduelo/nommand-toolkit --skill browser-pilot
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser-pilot
Source: https://github.com/PedroPaduelo/nommand-toolkit/tree/main/skills/browser-pilot
Command: npx skills add https://github.com/PedroPaduelo/nommand-toolkit --skill browser-pilot

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates manual, error-prone web interactions by automating navigation, form filling, data extraction, and debugging so teams can obtain reliable web data and reproduce UI workflows without manual browsing.

Core Features & Use Cases

  • Robust Navigation & Session Management: Create and close automation sessions, manage tabs, and ensure page readiness before interacting.
  • Data Extraction & Scraping: Extract text, tables, links, HTML, and styles; support pagination and structured outputs.
  • QA, Debug & Monitoring: Capture network, console, and WebSocket logs, take screenshots, collect performance metrics, and validate UI rules.
  • Advanced Interactions: Fill complex forms, select options, run custom JavaScript, perform batch actions, and use retry/backoff for flaky elements.
  • Use Case: Log into an authenticated SPA, extract a product table across pages, and produce a validated CSV with screenshots and network diagnostics.

Quick Start

Open a browser session to the target site, wait for the page to be ready, extract the main data table and a screenshot as evidence.

Frequently Asked Questions about browser-pilot

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

FAQPage Schema
How do I automate web scraping on an authenticated single-page application?

You can automate web scraping on an authenticated SPA by creating a browser session, managing the login flow, and using retry with backoff for flaky elements to reliably extract structured data.

Can I capture network requests and console logs during browser automation?

Yes, browser automation can capture network, console, and WebSocket logs during a session to perform QA diagnostics, collect performance metrics, and validate UI rules while interacting with a website.

What is the best way to extract paginated tables from a website into a structured format?

The best way to extract paginated tables is to navigate across pages, extract text and HTML elements, and output the collected data as a structured file alongside screenshot evidence.

How do I handle flaky elements when filling out complex multi-step forms?

You can handle flaky elements during form filling by using retry with backoff strategies, ensuring page readiness before interaction, and executing batch actions to complete multi-step workflows.

Does browser automation work for taking screenshots as QA evidence?

Yes, browser automation supports taking screenshots during web interactions to provide visual evidence for QA diagnostics, validate UI workflows, and debug extracted data outputs.

Why does my web scraping script fail when navigating dynamic single-page applications?

Web scraping scripts fail on SPAs when page readiness is not ensured before interaction; using session lifecycle management, element-level actions, and script execution helps robustly navigate dynamic content.