Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Today, we’re introducing Skills in Chrome, a new way to build one-click workflows for your most frequently used AI prompts — like asking for ingredient substitutions to make a recipe vegan, generating side-by-side shopping comparisons across multiple tabs, or scanning long docs to get the info you need quickly....

1,283,015 görüntüleme • 5 ay önce •via X (Twitter)

36 Yorum

Google profil fotoğrafı
Google5 ay önce

We’re also launching a library of ready-to-use Skills for common tasks and workflows. You can save these Skills to your own library, and even customize them to better fit your needs by updating the prompt.

Google profil fotoğrafı
Google5 ay önce

Learn more about Skills in @GoogleChrome ↓

Alex Castle profil fotoğrafı
Alex Castle5 ay önce

@googlechrome

Kingsley Uyi Idehen profil fotoğrafı
Kingsley Uyi Idehen5 ay önce

Demonstrating the skills integration feature of the Gemini extension for Chrome. Steps in the demo: 1. Visit a page of interest 2. Invoke the Gemini extension (beside the address bar) 3. Use “/” to trigger skill lookup and selection 4. Select a skill 5. Enjoy! In my case, I generated a knowledge graph directly from the content of the page, which I then uploaded to a live #VirtuosoRDBMS instance via its SPARQL query services endpoint.

Himanshu Sahoo profil fotoğrafı
Himanshu Sahoo5 ay önce

@googlechrome Google spent 3 years losing the AI race then remembered they own the browser 💀

Sahil Panhotra | Indie Builder profil fotoğrafı
Sahil Panhotra | Indie Builder5 ay önce

@googlechrome i still don't get it where is this option i am not able to find it or does this requires latest chrome

Drew Zain profil fotoğrafı
Drew Zain5 ay önce

@googlechrome Sounds more like a prompt library than a skill. So much for standardization 😑

Syd profil fotoğrafı
Syd5 ay önce

@googlechrome Something similar, but much more powerful. Free and Open source:

Sanket profil fotoğrafı
Sanket5 ay önce

@googlechrome Is any of the Google Chrome feature available in UK. Chrome is doing persistently US-only launches. It's frustrating now.

George profil fotoğrafı
George5 ay önce

@googlechrome Google turning Chrome into an agent playground is actually pretty smart. Saved prompts that run across tabs with just a slash? Finally makes AI feel useful instead of another tab I forget about.

Elisa profil fotoğrafı
Elisa5 ay önce

@googlechrome Holy shit my names there lol

Anton P. 👽 profil fotoğrafı
Anton P. 👽5 ay önce

@googlechrome This is not Skills... it is just a prompt library 🙃

Nitesh profil fotoğrafı
Nitesh5 ay önce

@googlechrome One click workflows sound clean but the real friction is context switching between tabs. Does it actually remember what you were doing 3 clicks ago?

Gen-ai profil fotoğrafı
Gen-ai5 ay önce

@googlechrome yeah and when is this coming outside U.S , canada, india and new zealand?

keshav profil fotoğrafı
keshav5 ay önce

@googlechrome let me guess, US only?

Caleb Fender profil fotoğrafı
Caleb Fender5 ay önce

@googlechrome This and vertical tabs made me re-download chrome after using Perplexity for nine months. Testing it out now

EPOXY EXPERT DESIGN profil fotoğrafı
EPOXY EXPERT DESIGN5 ay önce

@googlechrome I'm tired of waiting for Gemini on Chrome in my country.

Armaan Sidhu profil fotoğrafı
Armaan Sidhu5 ay önce

The browser is becoming the operating system. And every AI company just realized it at the same time. Google just shipped "Skills" for Gemini in Chrome — reusable AI workflows that run across any webpage with one click. This isn't a feature announcement. It's Google's answer to a war that broke out in the last 90 days. OpenAI launched Atlas (its own browser). Perplexity launched Comet. The Browser Company launched Dia. Anthropic shipped Claude for Chrome. Every major AI lab simultaneously concluded that the browser — not the chatbot, not the API, not the app — is where AI agents will live. Google's move is the most consequential because they already own the distribution. Chrome has 65%+ global browser market share. That's 3.5 billion devices where Gemini can be the default AI layer between the user and every website they visit. OpenAI can build Atlas. Perplexity can build Comet. But Google doesn't need anyone to download a new browser. They push an update and 3.5 billion people have AI Skills in their sidebar tomorrow. Here's how Skills work. You write a Gemini prompt — "analyze the protein macros in this recipe," "compare specs across these three product tabs," "scan this document for the key legal terms" — and save it as a reusable Skill. Next time, type "/" in the Gemini sidebar, select the Skill, and it runs against whatever page or pages you're viewing. One click. No retyping. It works cross-tab, so you can run a comparison Skill against five open browser tabs simultaneously. Google is also shipping a pre-built Skills library — productivity templates, shopping comparisons, research workflows, budgeting tools — so users who've never written a prompt in their life can start using AI agents immediately. That's the distribution play. You don't need to be a power user. You open Chrome, you click a Skill, AI does the work. The deeper signal is what Google announced a week ago alongside Skills: auto browse. For AI Pro and Ultra subscribers, Gemini can now handle multi-step tasks autonomously in the browser — booking appointments, ordering groceries, filling out forms. You tell it what you want, it navigates websites and completes the workflow while you do something else. This is the same trajectory as Anthropic's Claude Code Routines (which we covered earlier today) but applied to the consumer web instead of developer workflows. Claude Code automates your codebase. Chrome Skills automate your browser. The pattern is identical: define a workflow once, let AI execute it repeatedly without human intervention. The competitive dynamics are fascinating. Anthropic has Claude for Chrome as an extension — powerful but requires installation and a separate account. OpenAI built an entire browser because they had no distribution. Google just ships it as a Chrome update. The advantage of owning the browser is that you don't need permission to integrate. You ARE the integration layer. The risk for Google is that Skills and auto browse turn Chrome into a surveillance engine that knows not just what you browse but what you DO — what you buy, what you compare, what you skip, what you return to. Every Skill execution is a signal. Google's ad business already knows what you search for. Now it'll know what you do with the results. For users, the practical upside is real. If you do repetitive research, comparison shopping, document scanning, or content analysis across websites, Skills eliminates the friction of retyping prompts. It's the macro button for AI-powered browsing — simple, obvious, and the kind of feature that makes people use Gemini daily instead of occasionally. The AI browser war isn't about who has the best model. It's about who owns the surface area between the user and the internet. Google just reminded everyone that they've owned it for 17 years.

Agastya profil fotoğrafı
Agastya5 ay önce

@googlechrome This is the feature nobody asked for but everyone needed. Google cooking. 🔥

Yann Kronberg profil fotoğrafı
Yann Kronberg5 ay önce

@googlechrome This is what makes a browser stop being a reader and become an operator

Bill Zahalan profil fotoğrafı
Bill Zahalan5 ay önce

@googlechrome "new way to build one-click workflows" is doing a lot of work for what is basically saved prompts in the browser. but if that's all it takes to get normal people using AI consistently, fine.

kottley🦬 profil fotoğrafı
kottley🦬5 ay önce

@googlechrome Don’t see Chrome Skills on my Desktop macOS browser. Gemini Pro account. US based.

Ashwini profil fotoğrafı
Ashwini5 ay önce

@googlechrome Rooting for Google here. Their Skills make AI feel simple and usable for almost anyone, which is huge. But leading the AI scene takes more than convenience. It needs bold bets and real moonshots. Google has the muscle to do both… just waiting to see them truly take the lead.

MALATJI (2026) 🇿🇦 profil fotoğrafı
MALATJI (2026) 🇿🇦5 ay önce

@googlechrome Google introduced a "skill," which is basically a frequently used prompt. Similar to Claude, this is a nice-to-have feature for routine human-AI tasks.

Red Emano profil fotoğrafı
Red Emano5 ay önce

@googlechrome Google - how I wish you already activated these features in google chrome for macbook here in the Philippines!

Shahid profil fotoğrafı
Shahid5 ay önce

@googlechrome UK ETA ??

Julius profil fotoğrafı
Julius5 ay önce

@googlechrome Saving repeat prompts as one click workflows inside the browser makes this genuinely practical for everyday use

Andortum profil fotoğrafı
Andortum5 ay önce

@googlechrome this is cool but most people won’t realize the real play, you can chain these skills with multi tab context and basically turn chrome into a lightweight agent that does research + comparison + extraction in one click

Mojofull profil fotoğrafı
Mojofull5 ay önce

@kazunori_279 @googlechrome 日本でも早くGeminiを使えるようにしていただければと思います

Austin profil fotoğrafı
Austin5 ay önce

@googlechrome @dialtala

⟁ndrew V profil fotoğrafı
⟁ndrew V5 ay önce

@googlechrome / / / / skillz for dayz

Keiran Brown profil fotoğrafı
Keiran Brown5 ay önce

@googlechrome @GoogleAds urgent – account wrongly suspended, €3k payment taken but not applied, 3 duplicate €1,000 direct debits triggered. Losing revenue daily. Need escalation now.

yodo 👽 profil fotoğrafı
yodo 👽5 ay önce

@hnshah @googlechrome one-click ai workflows? might actually save my sanity

Mike H. Terris profil fotoğrafı
Mike H. Terris5 ay önce

@googlechrome That’s a good direction but Dia by @browsercompany (@Atlassian) is superior in almost every way. @joshm, let’s get some advertising going!

Max Wins profil fotoğrafı
Max Wins5 ay önce

@googlechrome and let me fucking guess, its only available is the fucking US?

Simon 🎮 profil fotoğrafı
Simon 🎮5 ay önce

@googlechrome Skills in Chrome means your most used AI prompts now live in your browser like bookmarks but they actually do something

Benzer Videolar

how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour: 1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time. 2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional. 3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file. 4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer. 5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent. 6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded. 7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded. 8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge. you can watch below shoutout to Meng To for coming on The Startup Ideas Podcast (SIP) 🧃 and walking through his full workflow. if you want to use AI to actually build gorgeous designs, you'll want to use see this. watch

GREG ISENBERG

512,753 görüntüleme • 5 ay önce