$npx skillfedfor your agent

Chrome

This skill lets you command Chrome directly through code, enabling you to build bots that navigate websites, extract information, and perform repetitive web tasks automatically. Perfect for workflow automation, testing, and data collection at scale.

Chrome lets you control the browser programmatically by sending commands through its remote debugging protocol or automation APIs. You can write scripts that navigate to URLs, click elements, fill forms, extract data, and perform any action a user would do manually. This enables you to build bots for workflow automation, testing, and data collection without manual intervention.

AI-generated summary based on this skill's SKILL.md

24 6 unlicensed, metadata onlyupdated by johnlindquist

Decision gist · record as of 2025-12-19

Chrome lets you control the browser programmatically by sending commands through its remote debugging protocol or automation APIs. You can write scripts that navigate to URLs, click elements, fill forms, extract data, and perform any action a user would do manually. This enables you to build bots for workflow automation, testing, and data collection without manual intervention.

manual: git clone https://github.com/johnlindquist/claude → cp -r claude ~/.claude/skills/chrome

Use it when

  • Yes, Chrome supports headless automation, which runs the browser without a visible UI—ideal for automated testing, CI/CD pipelines.
  • Chrome remote debugging exposes the browser's internals through a debugging protocol, allowing external scripts and tools to inspect.
Same gist for agents: .md · .json

Install

johnlindquist/claude/chrome · repository language: TypeScript

generated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do you automate Chrome with scripts?

Chrome lets you control the browser programmatically by sending commands through its remote debugging protocol or automation APIs. You can write scripts that navigate to URLs, click elements, fill forms, extract data, and perform any action a user would do manually. This enables you to build bots for workflow automation, testing, and data collection without manual intervention.

Can Chrome browser automation handle headless mode for testing?

Yes, Chrome supports headless automation, which runs the browser without a visible UI—ideal for automated testing, CI/CD pipelines, and server-side tasks. Running Chrome headless is faster and more resource-efficient than running with a full graphical interface, making it perfect for large-scale web automation and batch processing.

What is Chrome remote debugging and how does it integrate with automation?

Chrome remote debugging exposes the browser's internals through a debugging protocol, allowing external scripts and tools to inspect, control, and interact with the browser. Chrome automation frameworks leverage this protocol to launch instances, manage tabs, execute JavaScript, capture screenshots, and monitor network activity—giving you complete programmatic control over Chrome's behavior.

How can you launch and manage Chrome instances programmatically?

Chrome lets you spawn and manage browser instances directly from code, controlling when they start, which profile they use, and when they shut down. You can launch multiple Chrome instances in parallel, manage individual tabs within each instance, and orchestrate complex workflows across many concurrent browser sessions for large-scale automation tasks.

What web tasks can Chrome browser control automate?

Chrome automation excels at repetitive web tasks: navigating sites, extracting structured data, filling and submitting forms, taking screenshots, monitoring page changes, and interacting with dynamic content. It's widely used for price monitoring, lead generation, content scraping, automated testing, and any workflow that would otherwise require manual browser interaction.

Is Chrome suitable as a browser automation skill for building bots?

Absolutely. Chrome is one of the most popular choices for browser automation because it offers powerful APIs, excellent debugging support, and wide compatibility with web applications. The skill lets you build reliable bots that navigate websites, extract information, and perform repetitive web tasks automatically at scale, making it ideal for workflow automation and data collection projects.

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Automate browser interactions and web tasks using Chrome”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

puppeteer-automation
by Mindrally · Mindrally/skills

This skill teaches you how to harness Puppeteer for programmatic browser control, from launching headless instances to navigating pages and extracting data at scale. You'll discover patterns for reliable web scraping, form automation, and performance testing without manual intervention. Perfect for developers building data pipelines or testing complex web applications.

Apache-2.0updated Jun 2026
★ 202repo stars
Browser
by duck4nh · duck4nh/antigravity-kit

This skill enables you to programmatically control web browser operations, from navigating to URLs and clicking elements to filling forms and extracting page content. Integrate browser automation directly into your SkillFed workflows for seamless web interaction and data collection tasks.

no license declared → metadata onlyupdated Feb 2026
★ 14repo stars
puppeteer-skill
by LambdaTest · LambdaTest/agent-skills

This skill enables agents to create and execute Puppeteer automation scripts for comprehensive browser testing and web data extraction workflows. Leverage headless browser control to automate interactions, validate page behavior, and gather web content programmatically. Built by TestMu AI (formerly LambdaTest) and available under the MIT license.

MITupdated Jul 2026
★ 339repo stars
browser-rendering
by null-shot · null-shot/cloudflare-skills

This skill enables agents to render and interact with JavaScript-heavy websites through Cloudflare's infrastructure, extracting structured data from pages that require browser execution. Built for the Agent Skills standard, it integrates seamlessly with Claude, OpenAI, and other compatible agent platforms to handle complex scraping workflows at scale.

Apache-2.0updated Jan 2026
★ 0repo stars
Playwright
by EliasOulkadi · EliasOulkadi/shokunin

This skill harnesses Playwright's cross-browser automation capabilities to streamline testing workflows. Automate complex user interactions like authentication, data entry validation, and link integrity checks, then capture visual evidence through screenshots—all without manual intervention.

MITupdated Jul 2026
★ 110repo stars
ui-demo
by affaan-m · affaan-m/ECC

ui-demo lets you create polished demonstration videos of web applications by recording user interactions with a visible cursor and natural pacing. Ideal for building compelling product walkthroughs, tutorial content, and UI showcases that feel authentic and engaging to viewers.

MITupdated Jul 2026
★ 234,207repo stars

More skills Playwright Skill (unlicensed) · playwright (MIT) · Browser Automation Framework (unlicensed) · playwright-skill (MIT) · Playwright Skill (NOASSERTION) · Dev Browser (NOASSERTION) · puppeteer (MIT) · dev-browser (MIT)

Tags
browser-automationweb-scriptingchrome-controlheadless-browsingprocess-managementdevtools-integrationtab-manipulationremote-protocol