Google Chrome’s New AI Skills: How to Use Them
▼ Summary
– Google Chrome has introduced a new generative AI feature called “Skills,” which are repeatable AI prompts activated by keyboard shortcuts.
– Users can create custom Skills using the Gemini chatbot or choose from over 50 premade prompts for tasks like summarizing videos or modifying recipes.
– To use a Skill, users open the Gemini sidebar, type a forward slash, and select a prompt, which then analyzes information from shared browser tabs.
– Users can disable the feature by turning off the “Gemini in Chrome” toggle in Settings, which removes the “Ask Gemini” button from the browser.
– Competitors like Opera Neon offer a similar tool called “Cards,” indicating a broader industry trend toward reusable AI prompts in browsers.
Google Chrome has introduced a new generative AI capability called Skills, allowing users to execute repeatable AI prompts directly within the browser using simple keyboard shortcuts. This addition continues the tech giant’s strategy of embedding AI-powered tools across its software ecosystem to enhance user productivity and streamline online tasks.
To access this feature, users can click the “Ask Gemini” sparkle icon located in the browser’s upper-right corner to open the Gemini sidebar. From there, typing a forward slash in the prompt box reveals a library of over 50 premade Skills designed for various purposes. These preset prompts can instruct Google’s AI to perform actions like summarizing YouTube video content, optimizing recipes for higher protein, or analyzing job postings. Users also have the flexibility to create and save their own custom Skills using the Gemini chatbot.
Once a Skill is selected, Gemini processes the information from any browser tabs the user has shared, operating within the specific guidelines defined by the prompt. For example, the “Protein Maximizer” Skill provides a detailed framework: it analyzes a recipe webpage, identifies ingredients and their protein content, suggests substitutions to boost protein without altering the dish’s core flavor, and outputs a revised recipe with a complete nutritional breakdown. This structured approach aims to deliver consistent, useful results directly within the user’s workflow.
Early adopters and productivity-focused users may find these tools valuable for automating repetitive research and analysis tasks. However, as with many new AI integrations, some initial instability is possible, with performance likely improving through subsequent updates. It’s also probable that a significant portion of everyday Chrome users will remain unaware of the feature unless they actively seek it out.
For those who prefer a cleaner interface, the Ask Gemini button can be disabled. Users need to navigate to Settings, open the AI Innovations tab, and locate the Gemini in Chrome section. Turning off the main toggle on that page will remove the sparkle icon from the browser window entirely.
This launch represents another step in Google’s broader initiative to reimagine Chrome for the AI era. Earlier this year, the company integrated Gemini directly into the Chrome sidebar, positioning it as a persistent assistant for on-the-fly web queries. While Google has also tested more autonomous AI agents that can browse independently, current development efforts appear concentrated on these user-directed tools like Skills.
The concept of reusable AI prompts is gaining traction beyond Google. Competitors like the Opera Neon browser offer a similar system called Cards, where users can save their own prompts or choose from a curated library for tasks such as trip planning or organizing movie nights. This trend suggests a growing focus across the industry on making advanced AI functionality more accessible and repeatable for everyday browsing.
(Source: Wired)
