Google is bringing a new feature to Gemini in Chrome that lets you save and reuse your favorite AI prompts.

“Skills in Chrome,” as Google calls it, is a slightly confusing name, as we’re not talking about skill.md agent skills with complex instructions for a large language model (LLM). Instead, this is mostly a way to save a prompt you may want to regularly reuse. Indeed, it’s more akin to bookmarked prompts than instructions for AI agents, writes Senior Editor for AI Frederic Lardinois.

About calling it “skills” — the exact term Anthropic uses for its multi-step instruction feature in Claude — Lardinois tells me it’s “rather confusing, given that ‘skill’ now has an established meaning in the context of AI agents.” Nevertheless.

The canonical example provided by Google is saving a prompt that substitutes the ingredients in a recipe for vegan alternatives. Chances are, you have found yourself in a similar situation where you regularly write the same prompts (and maybe save a few in a text expander tool), whether that’s for personal use or for work tasks.

Go deeper: Google’s Gemini in Chrome now lets you save prompts as “skills”

More interesting reads for your Tuesday:

◌ Can you make Kubernetes invisible? Here’s why AWS is on a mission to do it.

◌ Claude Mythos Preview completes full cyberattack simulation for the first time

◌ Beyond the VPN: Cloudflare Mesh builds a private network for the age of AI agents

When agents lose context, stall mid-response, or vanish across tabs, these are not edge cases. They’re fundamental UX failures rooted in the missing layer of your AI stack: durable sessions. This is where AI applications break at scale.

As Kubernetes scales, manual patching and infrastructure drift often become bottlenecks that stall your roadmap and create compliance risks. Catch the replay to move beyond a coping-based strategy and adopt an API-driven foundation that scales without increasing your headcount.