google/skills

Agent Skills for Google products and technologies

What it solves

This repository provides a library of "Agent Skills"—pre-defined instructions and capabilities that allow AI agents to interact with, manage, and troubleshoot Google Cloud services and other Google developer platforms. It solves the problem of enabling AI agents to perform complex technical tasks, such as infrastructure configuration, database management, and security auditing, without requiring manual intervention.

How it works

These skills are modular packages that can be installed into various agent harnesses (such as Claude Code, Codex, or the Antigravity CLI) using a simple command-line interface. Each skill contains the necessary logic or instructions for an agent to execute specific workflows, such as generating monitoring queries, diagnosing GKE performance issues, or managing IAM policies. The project also includes plugins that bundle these skills with Model Context Protocol (MCP) servers to bridge the gap between the agent and Google's APIs.

Who it’s for

This project is for developers and engineers building AI-powered automation or agents who need to integrate Google Cloud and Google developer tools into their workflows. It is particularly useful for those looking to automate cloud infrastructure management, AI/ML model deployment, or security operations.

Highlights

  • Extensive Library: Includes hundreds of specialized skills covering Google Cloud, GKE, BigQuery, Security Command Center, and Google Ads.
  • Cross-Platform Compatibility: Works with multiple agent harnesses including Claude Code and other MCP-compliant environments.
  • Infrastructure Automation: Provides ready-to-use skills for complex tasks like TPU performance diagnostics, cost optimization, and Well-Architected Framework compliance.
  • Easy Integration: Simple installation via npx allows developers to quickly add specific capabilities to their existing agent setups.

Related

  • Project
    google/agents-cli

    A CLI and skill set for building, evaluating, and deploying enterprise-grade AI agents on the Gemini Enterprise Agent Platform using Google Cloud.

  • Project
    msitarzewski/agency-agents

    The repository provides a library of markdown‑based AI‑agent prompts (e.g., Front‑end Developer, AI Engineer, Prompt Engineer) and scripts to install them into various LLM‑powered coding assistants such as Claude Code, Cursor, Gemini CLI, etc. A companion desktop app automates installation. It’s a prompt‑template collection, not a model‑training framework.

  • Project
    kangarooking/kangarooking-skills

    A collection of structured, open-source Agent Skills compatible with the Agent Skills standard, providing reusable workflows for content creation, image generation, and AI project engineering.

  • Project
    LambdaTest/agent-skills

    Agent‑Skills is a Node‑JS CLI that adds AI‑assistant‑driven test‑automation “skills” (Selenium, Playwright, Cypress, etc.) for the TestMu AI cloud platform, letting LLMs generate and run tests directly on the service.

  • Project
    sanjay3290/ai-skills

    A collection of portable, standardized skills for AI coding assistants that enable them to interact with databases, productivity tools, and cloud infrastructure.