Gemini is here to stay, but some of the habits we’ve picked up along the way will have to go.
As of today, the Gemini experience, be it on the standalone app or via one of its several integrations, like Chrome, can feel very repetitive.
Google wants to change that, and it is starting to do so with a new ‘Skills’ feature for Gemini in Chrome.
I almost ignored the Gemini button in Chrome, but now it saves me hours every week
The Gemini Ask button is more useful than it looks
The repetitiveness is especially common when it comes to prompts, and to alleviate the fatigue, Google is rolling out Skills that can turn some of your most used prompts into one-click workflows.
“Until now, repeating an AI task — like asking for ingredient substitutions to make a recipe vegan — meant re-entering the same prompt as you visited different pages. To make this easier, we’re launching Skills in Chrome, which lets you save and reuse your most helpful AI prompts and run them with a single click,” wrote the tech giant.
The tech giant explains that if and when you write a Gemini prompt that you know you’ll want to use again, you can simply save it as a Skill directly from your chat history.
You’ll be able to give the Skill a name and fine tune the instructions/prompt, as seen in the short GIF below, where a user makes a skill out of their prompt about analyzing a recipe, estimating its protein content, and suggesting substitutions and additions to maximize the overall protein content of the recipe.
For this user, any subsequent recipe analysis is just a Skill away without them needing to type out the whole prompt again. Here’s what that workflow might look like:
- Type a forward slash (/) or click the plus sign (+) in the Gemini sidebar to trigger a skill. The skill will then run on the page you’re viewing, along with any other tabs you select.
- You can edit your saved skills or create new ones at any time.
- Those that do not want to create their own Skills will be able to leverage commands from a new “library of ready-to-use Skills.” Said library will be found at chrome://skills/browse. It’s worth noting that the page isn’t live just yet.
Early use has proven that Skills can be used for a variety of workflows. Here are a few examples:
- Health & Wellness: quickly calculating protein macros for any recipe
- Shopping: generating side-by-side spec comparisons across multiple tabs
- Productivity: scanning lengthy documents for important information
Will you be creating Skills for frequently used prompts? Share your ideas below!
