Google is bringing a new feature to Gemini in Chrome that lets you save and reuse your favorite AI prompts.“Skills in Chrome,” as Google calls it, is a slightly confusing name, as we’re not talking about skill.md agent skills with complex instructions for a large language model (LLM). Instead, this is mostly a way to save a prompt you may want to regularly reuse. Indeed, it’s more akin to bookmarked prompts than instructions for AI agents.The canonical example here from Google is saving a prompt that substitutes the ingredients in a recipe for vegan alternatives. Chances are, you have found yourself in a similar situation where you regularly write the same prompts (and maybe save a few in a text expander tool), whether that’s for personal use or for work tasks.This new feature is now rolling out to all Chrome desktop users on Mac, Windows, and ChromeOS, with their language set to English-US. Now, in Chrome, all you have to do is run the prompt and save it. To run it again, you either type forward slash and auto-complete your saved prompt, or click on the plus sign in the Gemini sidebar to bring up your library of prompts. Existing skills can be edited and deleted as needed, and if you are an AI Pro or Ultra subscriber, the prompts can also include actions that rely on Google’s Auto-Browse feature for Gemini, which can browse the web for you.Google stresses that these skills will come with built-in guardrails, just like for any other action Gemini takes in the browser. It will ask for confirmation before adding events to your calendar or sending an email, for example.Availability of Skills in ChromeThis new feature is now rolling out to all Chrome desktop users on Mac, Windows, and ChromeOS, with their language set to English-US. They’ll be available to all users, even those who do not subscribe to one of Google’s AI plans. Once you’re signed in and have saved a skill, it will sync with any other desktop device where you sign into Chrome.Competition To some degree, it feels like Google is playing catch-up here. Anthropic’s Claude for Chrome, for example, has long allowed you to save tasks and run them on a schedule. It also lets you record workflows to replay later (and annotate them by voice for better results).Atlas, ChatGPT’s browser, also lets you save prompts for reuse, though it doesn’t look like OpenAI is putting all that much emphasis on Atlas now that it is focused on building a ‘superapp.’Dia, The Browser Company’s dedicated AI browser, unsurprisingly features similar capabilities (which it also calls ‘skills’), as well as a pre-built library of prompts.The post Google’s Gemini in Chrome now lets you save prompts as “skills” appeared first on The New Stack.