Previously, when users assigned tasks to AI, they had to repeat the same prompt on every page. Now, there is a way to save, remix, and instantly reuse AI workflows.
Earlier this year, Google began updating Chrome, actively integrating AI into the browser experience. That’s when Gemini appeared in the Chrome sidebar, positioned as an always-available assistant that can answer questions directly about the page a user is viewing. Beyond that, Google has been experimenting with generative AI capabilities that can take control of the browser itself, such as navigating and browsing pages on behalf of the user. Now, the company is taking a step further in optimizing how AI tasks are executed within the browser.
How to use it
To start using the new feature, users need to click the “Ask Gemini” icon in the top-right corner of the screen, which opens the Gemini sidebar in Chrome. In the prompt field, typing a forward slash ( / ) allows users to select a Skill.
While using Gemini on any webpage, users can save a prompt directly from chat history as a Skill. To use it again, they simply need to type ( / ) or click the plus ( + ) button in the Gemini chat. The task will then run on the current page as well as across selected tabs. Saved Skills can be edited at any time, and new ones can be easily created.
Google highlights how early testers have been using Skills in Chrome – calculating protein content in recipes, generating side-by-side product comparison tables across multiple tabs, and analyzing documents to extract key insights. One example shared by Google is the following prompt, saved as a Skill called “Protein Maximizer”:
“Analyze the recipe on the current webpage, identify all ingredients, and estimate their protein content. Suggest substitutions or additions to maximize the overall protein content of the recipe, while maintaining the integrity of the original recipe’s flavor profile. Output the revised recipe with protein content listed for each ingredient and the total protein per serving.”
In addition, one of the use cases highlighted by Google is analyzing the ingredients of a cosmetic product directly on an online store page.
It’s also worth noting that users who do not want to use this feature or the Ask Gemini button can remove it via settings. To do this, go to Settings, open the AI Innovations tab, then navigate to the Gemini in Chrome section and turn off the top toggle. Once disabled, the Ask Gemini button disappears from the browser’s top bar.
Getting started with the Skills library
Users can also choose from a library of ready-made Skills. This library includes more than 50 preset templates covering common tasks that can be useful in everyday scenarios. Examples include:
- protein mix – modifies a recipe by suggesting high-protein additions
- gift concierge – helps select and refine the perfect gift
- dramatize content – elevates a story using cinematic, trailer-style language
Users can save any useful Skills, edit them, and adapt them to their own needs.
What about security?
Google states that Skills operate within Chrome’s security and privacy framework and use the same safeguards as Gemini prompts. Before performing actions such as adding calendar events or sending emails, Skills will request user confirmation, ensuring that control remains in the user’s hands. Additionally, Skills are protected by Chrome’s layered security mechanisms, including automated vulnerability testing and auto-updates.
Who is it available for?
The Skills feature is available by default to all Chrome users signed into their Google accounts, provided that the browser language is set to US English.
It is also important to note that Google is not the only company working to make AI prompts more reusable and efficient. According to Wired, a similar tool called Cards is offered by the Norwegian browser Opera Neon. Opera Neon users can also reuse their own prompts or choose from a preset library. Some of the most popular features in Opera Neon include tools for task prioritization, planning movie nights, and finding budget travel options.