Save prompts as reusable Skills
Turn a prompt you have already written into a reusable Skill directly from your Gemini in Chrome chat history, so you do not have to re-enter the same instruction each time.
Overview
Skills in Chrome is a Chrome feature for turning prompts you already use in Gemini in Chrome into reusable tools. Instead of retyping the same instruction every time you visit a new page, you can save a prompt as a Skill and run it again with a single click.
The feature is designed for browser-based AI workflows that benefit from context: a Skill can run on the page you are viewing and, when relevant, across other tabs you select. Google is also launching a library of ready-to-use Skills for common tasks, giving people a starting point before they customize their own prompts.
What Skills in Chrome does
Run workflows from the Chrome side panel
Trigger a saved Skill with a single action from Gemini in Chrome by typing `/` or selecting the `+` button, then run it on the page you are viewing.
Work across the page and selected tabs
Apply a Skill to the current page and, when needed, selected additional tabs, which makes it useful for tasks that pull information from multiple webpages.
Update Skills after saving them
Edit saved Skills and create new ones whenever your workflow changes, so the prompt behind the workflow stays customizable over time.
Use a starter library for common tasks
Start from Google’s library of ready-to-use Skills for common tasks, then save a useful one or customize it for your own workflow.
Built with Chrome security safeguards
Use Skills with Chrome’s built-in safeguards, including confirmation prompts for sensitive actions and layered protections such as automated red-teaming and auto-update capabilities.
Practical ways to use Skills in Chrome
Repeat a recipe workflow across pages
Save a prompt for ingredient substitutions or similar recipe adjustments, then rerun it on new recipe pages without typing the same request again.
Compare items across shopping tabs
Compare product specs across several tabs and use a Skill to gather the relevant details into one browser-based workflow.
Review lengthy documents faster
Scan long documents for key points, especially when you want a reusable prompt for summarizing or finding specific information.
Adapt a prebuilt workflow to your needs
Start from Google’s ready-made Skills for common tasks like breaking down product ingredients or choosing a gift, then edit the prompt to match your own criteria.
Work from multiple open tabs
Use a Skill that needs page context plus additional tabs when your task depends on multiple sources open in Chrome at the same time.
Pros and Cons
Pros
- Cuts repeated prompting by letting you save an AI workflow once and reuse it quickly.
- Can run against the current page and selected tabs, which suits browsing tasks that need context from multiple sources.
- Lets you edit and refine saved Skills instead of rebuilding prompts from scratch.
- Includes a library of starter Skills for common workflows, which lowers setup time.
- Uses Chrome’s existing security and privacy safeguards, including confirmation prompts for sensitive actions.
Cons
- The rollout is limited to Chrome desktop and, at launch, to Mac, Windows, and ChromeOS users with Chrome language set to English-US.
- The source does not explain how broad the Skills library is, beyond saying it covers common tasks.
- Skills still ask for confirmation before sensitive actions, so they are not fully hands-off automation.
FAQ
How do you create and run a Skill in Chrome?
Skills in Chrome are saved from your Gemini in Chrome chat history. After saving a prompt as a Skill, you can invoke it by typing `/` or clicking the `+` button in Gemini in Chrome.
Which devices and languages are supported?
No. The source says Skills are available on signed-in Chrome desktop devices, and the initial rollout is for Mac, Windows, and ChromeOS with Chrome language set to English-US.
Can a Skill use information from more than one tab?
Skills can run on the page you are viewing and can also use other tabs you select, which makes them useful for multi-tab workflows.
Do Skills take actions automatically?
Skills use the same safeguards as prompts in Gemini in Chrome. Sensitive actions such as adding a calendar event or sending an email require confirmation before they are completed.
Can I use prebuilt Skills instead of writing my own?
Google says it is launching a library of ready-to-use Skills for common tasks, and you can save, edit, and customize those prompts to fit your needs.
Quick Facts
- Category
- Browser AI workflow
- Product
- Skills in Chrome
- Platform
- Chrome desktop
- Availability
- Rolling out now; Mac, Windows, and ChromeOS; English-US Chrome language
- Source domain
- blog.google
- Primary use
- Save and rerun AI prompts as one-click tools
Skills in Chrome 替代品
Edgee
Edgee is an AI gateway for coding agents and LLM-powered apps. It compresses token traffic, routes requests across models, and provides observability and team controls to help reduce cost and keep sessions running.
Codex Plugins
Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI. They help extend Codex with connected-service tasks, reusable instructions, and shared team workflows.
Struere
Struere is an AI-native platform for turning spreadsheet data into structured operational software with dashboards, alerts, and automations. It is aimed at teams that want to replace manual spreadsheet workflows without building custom tools from scratch.
Prompty Town
Prompty Town is a web product that turns a link into a building in a small internet city. It appears to let users buy a tile, add a prompt, and publish the result alongside other buildings.
OpenFlags
OpenFlags is an open-source, self-hosted feature flag platform for modern JavaScript teams. It supports local evaluation, targeted rollouts, and controlled launches while keeping flag data in your own infrastructure.
Creativly
Creativly 是一款基于网页的 AI 创意工作室，可用简短输入快速生成视觉概念、样机和风格化图片，适合设计师、创作者和创业者进行快速视觉构思。