Back to directory

Agent Skills

A collection of Agent Skills for Google Cloud and other Google products, installable into AI coding agents, covering onboarding, authentication, Kubernetes administration, BigQuery, Genkit, the Gemini API and multi-product solution architectures.

Agent Skills

This repository packages Agent Skills for Google products and technologies, mainly Google Cloud, for an AI coding agent to install and use. Skills install selectively with a single command, letting a user pick specific skills from the repository.

The skills span getting started with Google Cloud, such as authentication, onboarding and foundation building; multi-product solution workflows, such as agent gateway security, agentic analytics and retrieval-augmented generation for enterprise search; AI/ML operations for an agent platform, including model tuning, deployment and prompt management; Genkit for Dart, Go, JavaScript and Python; and Google Kubernetes Engine infrastructure tasks such as cluster creation, autoscaling, backup and disaster recovery, and batch workloads.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.