Google replaces Gems with Skills, adopting Anthropic's agent-ready standard

Google is retiring Gems in favor of Skills, a standardized prompt format that positions reusable instructions as first-class agent primitives within Gemini. This shift mirrors OpenAI and Anthropic's moves toward interoperable, agent-ready architectures, signaling industry convergence on how AI systems will invoke and chain capabilities at scale. The migration, beginning November, reflects a broader pivot from chat-centric interfaces to structured, composable workflows that enable both user-triggered and autonomous execution patterns.
Modelwire context
Analyst takeGoogle isn't just renaming Gems; it's adopting the same standardized, composable prompt format that OpenAI and Anthropic have already moved toward. This signals that the real competition isn't over which vendor has the best agent, but over whose format becomes the portable standard that locks in developer mindshare.
This consolidation mirrors OpenAI's shift toward enterprise-grade, bounded agent workflows (covered in 'OpenAI connects the Dots' late September). Both moves reflect a vendor consensus that agents need to be packaged as reusable, interoperable primitives rather than monolithic chat experiences. Google's phone-calling experiments from late September showed the company testing real-world agency, but Skills signals a deeper architectural bet: that the future of agent deployment depends on standardized invocation layers, not novel UI wrappers. The timing matters. Meta's Muse agent launch (same day as this story) also operates on task-specific permissions and delegation, suggesting the entire industry is converging on the same architectural pattern simultaneously.
If Google, OpenAI, and Anthropic publish a shared Skills specification or cross-vendor compatibility layer within the next six months, that confirms the standardization play is real and not just marketing alignment. If Skills adoption among third-party developers exceeds Gems adoption by 3x within a year, the format has won; if migration stalls, it suggests developers view this as vendor lock-in rather than genuine portability.
Coverage we drew on
- OpenAI connects the Dots · Platformer
This analysis is generated by Modelwire’s editorial layer from our archive and the summary above. It is not a substitute for the original reporting. How we write it.
MentionsGoogle · Gemini · OpenAI · Anthropic · Skills · Gems
Modelwire Editorial
This synthesis and analysis was prepared by the Modelwire editorial team. We use advanced language models to read, ground, and connect the day’s most significant AI developments, providing original strategic context that helps practitioners and leaders stay ahead of the frontier.
Modelwire summarizes, we don’t republish. The Decoder originally reported this story as “Google drops Gems for Skills, joining OpenAI and Anthropic in the shift to agent-ready prompt formats”. The full content lives on the-decoder.com. If you’re a publisher and want a different summarization policy for your work, see our takedown page.