Google Is Replacing Gemini's Gems with 'Skills': What Happens to Your Custom AI Helpers (November 2026)


If you've built custom AI helpers in Google's Gemini — a running coach, a study tutor, a resume reviewer — there's a date to put in your calendar. Google has announced that Gems, its custom-assistant feature, will be replaced by a new system called "skills" starting November 17, 2026, according to reporting by TechCrunch. Google says existing Gems will be migrated automatically, so nothing you built disappears. But how you use them is changing, and the shift says a lot about where Google thinks assistants are heading. Here's what's happening and what to do before the switch.

What Google announced

Gems launched in 2024 as Gemini's answer to OpenAI's custom GPTs: you write instructions once — "you are my marathon coach, my race is in April" — and get a reusable assistant with its own name and personality. Some Gems could be shared with other people. Per TechCrunch's September 28 report, Google will transition Gems to skills on November 17, 2026. Until that date, Gems keep working as they do today.

What "skills" are and how they differ

Skills carry the same core idea — packaged custom instructions — but they live differently in the interface. Instead of opening a dedicated Gem and chatting inside it, you'll invoke a skill from within any conversation by typing a forward slash ("/") and picking the skill you want. In other words, Gems were places you went; skills are abilities you summon mid-task. That's a more technical-feeling interaction, closer to slash commands in Slack or Discord, and it means one conversation can draw on several skills rather than being locked to one persona.

What happens to the Gems you already built

According to the announcement, Google will migrate user-created Gems to the skills format automatically — you don't need to export or rebuild anything, and your instructions are preserved. That said, automatic migrations are a good moment for housekeeping. Before November 17, it's worth: reviewing which Gems you actually use and deleting dead ones; copying the instruction text of important Gems into a note as a personal backup; and checking any Gems you've shared with others, since sharing behavior may work differently after the change.

Why Google is doing this

Two forces are visible. First, competitive pressure: all-in-one agent products — Meta's Muse and the viral agent startup Instinct among them — treat capabilities as things an agent picks up fluidly mid-conversation, not as separate mini-bots you switch between. Second, Google's broader push toward agents: a skill that can be invoked inside any task composes better with an assistant that plans and executes multi-step work. The persona model of 2024 is giving way to a toolbox model. (TechCrunch's writer also notes, fairly, that Google has a habit of renaming features — so some of this is branding churn too.)

What it means for how you work

The practical upside: less context-switching. If you're drafting an email and want your "plain-English editor" skill, you'll call it right there with a slash instead of moving the text to a different Gem. The downside: discoverability. A list of named Gems on a home screen advertises itself; a slash menu requires you to remember what you have. Power users will likely benefit; casual users who liked tapping a friendly named helper may find the new model colder. If you rely on Gems today, spend the weeks before migration learning the slash-invocation habit.

The bigger pattern: custom assistants are converging

OpenAI's GPTs, Gemini's skills, and project/instruction features in other chatbots are all converging on the same idea: reusable instruction bundles that plug into a general agent. The skill you actually need as a user is writing a good instruction block — clear role, constraints, examples, output format. That skill transfers across every platform, whatever each vendor renames its container this year.

FAQ

Will my Gems be deleted on November 17, 2026?

No. Per Google's announcement as reported by TechCrunch, existing Gems will be automatically converted to skills, with their instructions preserved. You don't need to take action, though keeping your own copy of important instruction text is a sensible backup.

Do I need a paid plan to use skills?

Google hasn't framed the change as a paywall shift; Gems have been available broadly, and skills replace them in place. Plan details can change, so check Gemini's official help pages at rollout.

Are Gemini skills the same as ChatGPT's custom GPTs?

They solve the same problem — reusable custom instructions — but differ in interaction: GPTs are still separate assistants you open, while skills are invoked inside any conversation with a slash command.

Related on AI Learning Lab: How to Build Your Own AI Assistant with Custom GPTs, Gems, and Projects · Google Home Opens to Outside AI Agents: What MCP Support Means

Comments

Post a Comment

Popular posts from this blog

AI Search vs Traditional Search: How to Use Each in 2026

Image
Something changed in how people find things, and the numbers are unusually clear about it. According to a SparkToro analysis of Similarweb clickstream data published in June 2026, about 68% of U.S. Google searches between January and April 2026 ended without a click — up from roughly 60% in 2024. Answers are arriving without anyone visiting a page. That makes "which kind of search should I use?" a question worth having a real answer to. What the data actually says Two figures from that analysis matter most. AI Overviews now appear on more than 20% of Google searches, and click-through rates fall by roughly 60% when they do . The behavior shift is not that people stopped searching — it is that a search increasingly ends where it used to begin. For anyone doing research, the tradeoff is speed against provenance. You get an answer faster, and you can see less about where it came from. When AI search is the right tool You do not know the vocabulary yet — "the clause that l...
Read more

Free vs Paid AI Tools: When Is Upgrading Actually Worth It?

Image
Every AI assistant now has a free tier that's genuinely capable, and a paid tier that costs roughly the price of a couple of lunches per month. So the question isn't "is AI worth paying for" in the abstract — it's whether your specific usage crosses the line where paying changes anything . This article gives you that line. What you actually get when you pay Pricing and features shift constantly, so ignore the marketing lists and look at the three differences that persist across providers: Priority access. Free tiers get throttled or queued at busy hours. If your work happens during peak times, this is the difference between a tool you rely on and a tool that sometimes isn't there. The current top model. Free tiers usually route you to smaller or older models, with limited access to the best one. For simple tasks this doesn't matter. For reasoning-heavy work, it's the whole ballgame. Data handling. This is the one most people overlook. Paid and busin...
Read more

What Is a Small Language Model (SLM)? On-Device AI Explained

Image
Most of the attention in AI goes to models that get bigger. A quieter trend runs the other way: models small enough to run on a laptop, a phone, or a server in your own building. These are usually called small language models, or SLMs, and they are showing up inside products you already use — often without being announced. Here is what they are and when the small option is the better one. What counts as "small" There is no official threshold, but the working definition in most technical writing puts SLMs under roughly 10 billion parameters, with the common range falling between about 1 billion and 7 billion. Frequently cited examples include Microsoft's Phi-3 Mini at 3.8 billion parameters, Llama 3.2 3B, and Mistral 7B. The contrast is with frontier models, which run to hundreds of billions of parameters and, in the largest cases, over a trillion. Parameters are the adjustable values a model learns during training — loosely, a measure of how much the model can store. Fewe...
Read more