Google added Skills to Chrome for saving AI prompts and launching them in one click

Google has launched a new Skills feature in Chrome that turns successful requests to Gemini into reusable commands. Instead of retyping the same prompt on every website, you can save it and run it with one click on the current page or across multiple tabs simultaneously.

How Skills Work

Skills are built into Gemini in Chrome and designed for repetitive scenarios: quickly comparing products, extracting facts from long documents, checking product ingredients, or adapting recipes. When a user gets a useful result, they can save the prompt directly from the chat history, then invoke it with the "/" symbol or through the "+" button in the browser sidebar. The point of the update is not a new model, but packaging the prompt as a permanent tool.

The request remains editable: you can rewrite it, refine it for your specific task, or create several variations for different situations. Google specifically emphasizes that a saved Skill runs on the current page and can take other selected tabs into account if the task requires comparison or summarization from multiple sources at once. For Chrome, this is also a strategic move in the battle for the browser as the primary AI surface.

Instead of a separate app, Google is embedding repeatable scenarios directly into web browsing: where users read, compare, shop, and make decisions. Other players are also becoming active in this space right now, so betting on fast single-step AI actions within the browser looks quite pragmatic.

Ready-Made Scenarios

Along with user-created Skills, Google opened a library of pre-made templates for typical tasks. This should lower the barrier to entry for those who don't want to come up with successful formulations themselves and test them in Gemini. A found template can be added to your collection, and then edited to match your own work style if desired.

• Comparing product specs across multiple tabs
• Finding key points in long documents
• Calculating nutrients and macros in recipes
• Analyzing product composition before purchasing
• Finding a gift based on budget and person's interests

According to Google, early testers used Skills most often for shopping, productivity, and health and nutrition tasks. This shows where Chrome is pushing the built-in AI: not toward a separate chat window for experimentation, but toward regular browser actions that you want to repeat every day without copy-pasting the same instructions.

Launch and Limitations

Google began rolling out Skills on April 14, 2026 for Gemini in Chrome on desktop. At launch, the feature is available on Mac, Windows, and ChromeOS, provided the browser language is set to English (US). Saved Skills are synchronized across desktop devices where the user is logged into their Chrome account, so familiar AI scenarios can be transferred between work and home computers without manual setup.

Google also emphasizes user control. If a Skill leads to an action beyond a simple response—for example, adding an event to a calendar or sending an email—the browser should request confirmation. The company says the feature uses the same protective mechanisms as Gemini in Chrome, including Chrome's built-in security measures, automatic updates, and internal red teaming before release.

What This Means

For Google, this is a way to make Gemini in the browser more useful without making grand agent promises: the company sells not an "autonomous assistant," but a set of repeatable mini-workflows on top of the web. For users and teams, this is an important shift: the best prompt stops living in notes or old chats and becomes a button that can be run as needed on any suitable page.