skills.rest
AarnavBaddam
AarnavBaddamCOMMUNITY
Explore all skills by this author →
GitHub

control-in-app-browser

Controls the in-app browser to navigate, inspect, click, type, and screenshot web pages.

Updated Jul 31, 2026
Search Tags:#screenshots#browser automation#web testing#playwright#local development#page inspection#in-app browser
One-click install
npx skills add https://github.com/AarnavBaddam/skills --skill control-in-app-browser-aarnavbaddam
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: control-in-app-browser
Source: https://github.com/AarnavBaddam/skills/tree/main/control-in-app-browser
Command: npx skills add https://github.com/AarnavBaddam/skills --skill control-in-app-browser-aarnavbaddam

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? It lets you automate and inspect the in-app browser directly from a conversation, so you can open pages, test local web apps, and interact with page UI without leaving your workflow or manually driving a browser. ## Core Features & Use Cases - Browser Automation: Navigate to URLs, click elements, type into fields, and take screenshots of visible page state. - Local Web Testing: Open and verify local development pages and files inside the in-app browser, reusing existing signed-in sessions. - Smart Surface Selection: Automatically chooses between the in-app browser and Chrome, and prefers purpose-built connectors, APIs, or CLIs for semantic operations on linked resources. - Use Case: While developing a web app, ask the assistant to open your local dev server in the in-app browser, click through a flow, and screenshot the result to verify a UI change. ## Quick Start Open my local app at http://localhost:3000 in the in-app browser and verify the homepage loads correctly.

Frequently Asked Questions about control-in-app-browser

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

FAQPage Schema
How do I control the in-app browser from ChatGPT?▼

Ask the assistant to open a URL, click elements, type text, or take a screenshot in the in-app browser. The skill initializes a browser-client runtime through the Node REPL js tool and reuses the connection across turns.

How do I test a local web app in the in-app browser?▼

Provide your local server URL, such as http://localhost:3000, and ask the assistant to open and verify it. The browser can navigate, inspect visible page state, and capture screenshots of your local pages.

When should I use a connector or API instead of browser automation?▼

For semantic operations on linked resources, the skill requires checking for an applicable connector, API, or CLI first. Browser automation is used only when no such tool exists, it lacks access or capability, or UI interaction is required.

Can the in-app browser use my existing signed-in sessions?▼

Yes, the in-app browser can have existing signed-in sessions, so authenticated pages may work without re-login. If authentication blocks navigation, the assistant asks you to sign in rather than switching to another source.

Why does browser setup fail or browser discovery not work?▼

Setup failures are handled by reading built-in troubleshooting documentation: bootstrap-troubleshooting for discovery or selection failures, and chrome-troubleshooting for Chrome extension setup or communication issues.

Related Skills

Explore More Software Engineering Skills→
tangzheng202202tangzheng202202
1

dogfood

Identify and document web application defects through structured exploratory QA testing.

Community
Advanced
AmitabhainArunachalaAmitabhainArunachala

dharma-browse

Automates browser navigation, state verification, and screenshot capture for web inspection workflows.

Community
Basic
larsboeslarsboes

Browser

Automate multi-step browser workflows with Playwright CLI and visual validation.

Community
Advanced
softmgsoftmg

agent-browser

Guide Codex to reproduce local browser scenarios and capture evidence.

Official
Intermediate