If you're building on Vertex AI instead of the standard Gemini API, this is the skill you want. It covers the full range of capabilities: text generation, multimodal understanding across images/audio/video, function calling, structured outputs, and the newer stuff like context caching and the Live Realtime API for low-latency voice interactions. The big thing to know is it strictly uses the unified Gen AI SDK across all languages and explicitly avoids the legacy Vertex AI SDKs, which matters if you're migrating existing code or following older tutorials. Also includes batch prediction for large-scale async workloads, which is more of an enterprise feature you won't find in the consumer API.
npx -y skills add google-gemini/gemini-skills --skill vertex-ai-api-dev --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
prisma/skills
firebase/agent-skills
Dexploarer/hyper-forge
itsmostafa/aws-agent-skills
prisma/skills