Google to Replace Gems with Skills in Gemini App Starting November 17, 2026
Google will start migrating Gemini's custom Gems into a new feature called skills on November 17, 2026. Skills, introduced alongside Gemini Spark, let users invoke multiple custom instruction sets at once using a slash command in the prompt box.
Google will begin automatically migrating Gems to a new feature called skills in the Gemini app starting November 17, 2026, according to a notice spotted by 9to5Google in the Gems manager interface.
The notice reads: "Gems will become skills starting Nov 17, 2026... Starting November 17, 2026, we'll automatically begin migrating your Gems to skills. You will be able to use your Gems until they migrate."
What's changing
Gems, introduced in 2024 as "custom versions of Gemini," let users create tailored chatbot personas with default tools (such as Create Image or Canvas) and attached reference files. Users could also share Gems with others via links.
Skills, which Google introduced alongside Gemini Spark, serve a similar core purpose — giving Gemini custom instructions — but work differently in practice. Rather than navigating to a dedicated Gems section in the side panel and scrolling through a list, users invoke skills directly in the main chat by typing "/" in the prompt box. According to the report, multiple skills can be used simultaneously within a single conversation, a capability Gems did not offer.
Creating skills currently requires switching to the Gemini Spark tab, and is limited to Google AI Pro and AI Ultra subscribers. It's unclear whether free-tier users will get skill-creation access before or after the November migration.
Rollout appears early
9to5Google notes the announcement may have surfaced ahead of schedule: the "Learn more" help article linked from the notice does not yet resolve, and the "Create skills" button in the interface is non-functional as of this report. This suggests Google pushed the migration notice live before the underlying documentation and tooling were fully ready.
No pricing changes were mentioned alongside this transition — skill creation remains gated behind the same Pro/Ultra subscription tiers that currently unlock Gemini Spark.
What this means
This is a product restructuring, not a new model release — no new Gemini model or checkpoint is involved. Google is consolidating two overlapping customization systems (Gems and skills) into one, likely to simplify its product surface as Gemini Spark expands. The slash-command invocation and multi-skill support suggest Google is pushing toward a more composable prompting experience, closer to how developers chain tools or plugins mid-conversation, rather than the single-persona model that Gems represented.
For existing Gems users, the practical impact is a forced migration with automatic conversion rather than an opt-in choice — users keep access to their existing Gems only until the November 17 cutover, after which the underlying customization data presumably carries over into skill form. Given the non-functional help documentation at time of writing, expect further clarification from Google before the migration date on exactly what functionality, if any, is lost in translation (particularly around Gem-specific features like default tool selection and file attachments).
Related Articles
Google Tests 'Call for Me' Feature That Lets Gemini Make Phone Calls to Businesses
Google is testing 'Call for Me,' a feature that lets Gemini call businesses on a user's behalf to make reservations, reschedule appointments, or check stock. The beta is limited to Pixel 11 owners in the US with a paid Gemini subscription and Google's beta Phone app.
GitHub Copilot App Adds Canvases for Custom, Natural-Language-Built Workflows
GitHub has published a beginner's guide to canvases in the Copilot app, a feature that lets users describe an interface in natural language and have the agent build a live, interactive surface. The feature targets users who want custom workflow tools without writing code.
Google DeepMind Adds Real-Time Video Avatars to Gemini 3.8 Live
Google DeepMind has added Live Avatar, a real-time video avatar capability, to its Gemini 3.8 Live conversational model. The feature is available now in Gemini Enterprise, supporting lip-synced, expressive avatars across 97 languages with background tool calling.
Google's Gemini Can Now Make Full Phone Calls to Businesses on Your Behalf via Pixel 11
Google is testing a new Gemini feature on Pixel 11 that lets the AI place entire phone calls to local businesses—handling hold times, menu navigation, and conversations—on a user's behalf. The feature is rolling out as an 'early preview' to Gemini paid subscribers in the Phone by Google Public Beta.
Comments
Loading...