NEW Google Gemini CLI Update Is INSANE! 🤯

Google just dropped agent skills in the Gemini CLI. This thing can now run multi-step workflows automatically, plus image pasting, usage analytics, and way more. This is getting scary good. Let me show you what just changed. Hey, if we haven't met already, I'm the digital avatar of Julian Goldie, CEO of SEO agency Goldie Agency. Whilst he's helping clients get more leads and customers, I'm here to help you get the latest AI updates. Julian Goldie reads every comment, so make sure you comment below. Okay, so Google just released version 0. 23. 0 of the Gemini CLI, and this update is absolutely wild. They added five massive features that basically turn your command line into an AI automation powerhouse. I'm going to walk you through each one, show you exactly how to use them, and by the end, you'll see why this might replace a bunch of tools you're using right now. Let's start with the biggest one, agent skills. This is the game changer. So, what are agent skills? Think of them like plugins for your CLI, but instead of just adding commands, they add specialized expertise. The CLI can now invoke these skills automatically when it thinks they're relevant. You don't even have to ask for them. It just knows. Let me explain. Say you're working on content for the AI profit boardroom. You need to review code quality. With agent skills, you can create a code reviewer skill that automatically checks for style issues, security problems, and performance bottlenecks. The CLI sees what you're doing and activates that skill on its own. Here's how you set it up. First, install the preview version. Open your terminal and run npm install-g Google/gemini-li preview. That gets you the experimental build. Then, open your settings with the / settings command. Toggle experimental. sklls to true. That's it. You're ready. Now, here's where it gets interesting. Skills live in folders. You can put them in your project undergemini/skills or in your user folder at tilda/. mini/skills. Each skill is just a directory with a skill. md file inside. The file has YAML metadata at the top. Name, description, that stuff. Then below that, you write the actual instructions for what the skill does. The CLI reads these and knows when to use them. It's like giving your CLI superpowers for specific tasks. And here's the cool part. You can share skills with your team. package them up. Everyone gets the same workflows, same quality standards, same automation. This is huge for agencies running multiple projects. Think about it. You could build a skill that optimizes blog posts for SEO. Another one that generates email sequences. Another that reviews landing page copy. All of them sitting there ready to help whenever you need them. Okay. Next feature, Gemini CLI wrapped. This is basically Spotify wrapped but for your CLI usage. And it's actually really useful. you run mpx gemini dash wrapped in your terminal and it shows you everything. Top models you used, top programming languages, how many sessions you ran, usage trends over time. Why does this matter? Because you can see what's actually working. Maybe you're using Flash for quick tasks, but Sonet for complex ones, the stats show you that. Maybe you're spending way more time on Python than JavaScript. You'll see it for Teams. This is gold. You can track adoption, see who's using what, figure out which workflows are most popular, and if you're running an agency like we do, you can show clients how much automation you're doing for them. It's also just fun seeing your AI usage laid out like that. It's motivating, makes you realize how much you're actually leveraging these tools. All right, now we're about a third of the way through, and I want to tell you about something that's going to take all of this to the next level. If you're serious about using AI to automate your business and save tons of time, you need to check out the AI profit boardroom. This is where we share advanced strategies, workflows, and automation templates for tools exactly like this one. Imagine having ready-made agent skills that you can just drop into your CLI or having SOPs that show you exactly how to set up these workflows for client work or content creation. That's what you get inside. We've got a whole community building these automations together. So, if the Gemini CLI updates are exciting you, you're going to love what we're doing in there. Link is in the description. Now, let's keep going. Feature number three, clipboard image support for Windows. This one sounds simple, but it's actually a massive quality of life upgrade. If you're on Windows, you can now paste images directly into the CLI using Alt +V. That's it. Screenshot something. AltV. It's in your prompt. Why is this useful? Let's say you're debugging a website layout. Take a screenshot. Paste it into the CLI. Ask Gemini what's wrong with the design or you're working on ad creative, paste the mockup, get feedback on the copy and visual hierarchy. Before this, you had to save the image, reference the file path, upload it manually. Now it's instant, and that speed matters when you're moving fast on client projects or content production. Feature number four, terminal background detection. Okay, this one's more technical, but it's smart. The CLI now detects whether you're using a dark or

light terminal background, and it adjusts the color scheme automatically. It'll also warn you if there are accessibility issues with contrast. This matters because not everyone uses the same terminal setup. Some people use dark mode, some use light, some use custom themes. Before this update, certain text colors might be hard to read depending on your setup. Now, the CLI handles that for you. It's one of those things you don't think about until it's fixed. Then you realize how annoying it was before. The CLI just works better in more environments now. Less configuration, less troubleshooting, more time actually using it. Feature number five, the new logout command. Super straightforward. You can now run / logout to clear your credentials instantly. This is helpful if you're switching between Google accounts. Okay, let's talk about what all of this means together. Because individually, these features are cool, but combined they're changing how you can work with AI. Agent skills turn the CLI into a specialized assistant. It's not just answering questions anymore. It's running workflows. It's applying expertise. It's helping you complete complex tasks end to end. The analytics tool helps you optimize. You see what's working. You double down on it. You spot inefficiencies. You fix them. Image support removes friction. Visual tasks get faster. Feedback loops get tighter. Theme detection makes the tool more accessible. More people can use it comfortably. and the logout command makes account management simple. All of these together point to one thing. Google is serious about making the Gemini CLI a production tool, not just a demo, not just a toy, but something you can actually build your workflows around. And that's exciting because it means you can start automating parts of your business that were manual before. Content reviews, code audits, design feedback, client reporting, all of it can flow through the CLI now with these agent skills. Here's what I'd recommend. If you're already using the Gemini CLI, upgrade to the preview build today. Start experimenting with agent skills. Even if you just create one simple skill to start, get a feel for how they work. If you're not using the CLI yet, now's the time to try it. These updates make it way more powerful than it was even a week ago. And it's only going to get better from here. The key is to think about repetitive tasks in your workflow. Things you do over and over, those are perfect candidates for skills. Package them up. Let the CLI handle them automatically. That's where the real-time savings come from. All right, before we wrap up, I want to make sure you're getting the most out of AI automation because tools like this are just the beginning. If you want the full process, SOPs, and over a 100red AI use cases like this one, join the AI profit boardroom. Link is in the comments and description. You'll get all the video notes from there, plus access to our community who are absolutely crushing it with AI. We share workflows, templates, and strategies that you won't find anywhere else. is where the real automation magic happens. And if you're just getting started with AI and want to learn the fundamentals first, check out the AI Success Lab. It's our free community with over 40,000 members. You'll get access to foundational training, use cases, and a supportive group of people figuring this stuff out together. Also links below. If you want to stay ahead with AI, you need to be experimenting with tools like this. Download the preview build, set up a skill or two, see how it fits into your workflow. And if you found this helpful, make sure you're subscribed because AI updates like this are dropping constantly. I'm breaking them all down as they happen. Thanks for watching. Julian reads every comment, so drop your thoughts below, and I'll see you in the next