Chrome adds reusable 'Skills'
Google introduced 'Skills' in Chrome, letting users save and reuse AI prompts as one‑click workflows across tabs for tasks like recipe substitutions or document scanning. The feature was announced on Google's social channel and positions prompts as repeatable tools inside the browser (x.com).
Google is adding “Skills” to Chrome, a feature that lets people save an artificial intelligence prompt once and run it again with one click on other pages. (blog.google) Google announced the feature on April 14, 2026, and said users can save a prompt from Gemini in Chrome chat history, then call it back by typing a forward slash or clicking the plus button. The saved prompt can run on the page in view and on other tabs the user selects. (blog.google) Google’s examples are narrowly practical: vegan ingredient swaps on recipe sites, protein calculations for meals, side-by-side product spec comparisons, and scanning long documents for key points. Google is also launching a built-in library of ready-made Skills that users can add and edit. (blog.google) The feature sits inside Gemini in Chrome, the browser assistant Google started rolling out to Mac and Windows desktop users in the United States with Chrome set to English in September 2025. Google said that assistant can already answer questions across multiple tabs and connect with services including Google Docs and Google Calendar. (blog.google) What changes here is the unit of reuse. Instead of treating a prompt as a one-off chat message, Chrome now lets users keep it as a repeatable browser tool for the next page, the next shopping session, or the next document. (blog.google; techcrunch.com) Google said Skills use the same safeguards as prompts in Gemini in Chrome. If a saved prompt tries to do something like send an email or add a calendar event, Chrome asks for confirmation first. (blog.google) The launch also fits Google’s larger push to make Chrome itself an artificial intelligence product. In September 2025, Google described Chrome as an “AI-centric browser” and said it was adding tools for research, tab-level context, security, and task completion. (blog.google) Part of that push runs on Gemini Nano, Google’s smaller model for on-device browser features. Chrome’s developer documentation says those built-in artificial intelligence APIs are designed for desktops and laptops, not mobile devices, and require hardware such as at least 16 gigabytes of random access memory for some configurations. (developer.chrome.com) TechCrunch reported that Skills begin rolling out to Chrome desktop users signed into a Google account, with the feature initially limited to browsers set to English in the United States. That keeps the release aligned with Google’s earlier U.S.-first rollout pattern for Gemini in Chrome. (techcrunch.com; blog.google) Chrome has long been the place where people type the same searches, fill the same forms, and compare the same tabs. Google is now turning some of that repeated work into saved prompts that behave more like buttons than chats. (blog.google; arstechnica.com)