google-gemini/gemini-skills

Skills for the Gemini API, SDK and model/agent interactions

What it solves

It addresses the knowledge gap in LLMs caused by their fixed training data. Because software development evolves rapidly, models often lack awareness of the latest SDK changes, new libraries, or current best practices for using the Gemini API.

How it works

It provides a library of "skills"—lightweight context modules that can be added to AI coding assistants. These skills inject relevant, up-to-date information into the agent's context, allowing it to generate more accurate API code and follow current development standards.

Who it’s for

Developers building applications powered by the Gemini API, including those using the Gemini Live API, Interactions API, or Gemini Omni Flash for video generation.

Highlights

  • Improved Accuracy: Evaluations show that adding these skills increases an agent's ability to generate correct API code to 87% with Gemini 1.5 Flash and 96% with Gemini 1.5 Pro.
  • Bespoke Skill Sets: Includes specialized skills for real-time bidirectional streaming, multi-turn chat, structured output, and generative AI video editing.
  • Broad Integration: Compatible with various AI coding assistants and CLIs including Cursor, Claude Code, Vercel skills, and Context7.

Related

  • Project
    google/agents-cli

    A CLI and skill set that enables coding agents to build, evaluate, and deploy enterprise-grade AI agents on the Gemini Enterprise Agent Platform and Google Cloud.

  • Dispatch
    Gemini 3.7 Flash release notes / what's new

    Google DeepMind has released Gemini 3.7 Flash, a model optimized for coding and agents that offers significant performance gains over Gemini 3.6 Flash at half the introductory cost.

  • Project
    googleapis/python-aiplatform

    The Python SDK for the Gemini Enterprise Agent Platform (formerly Vertex AI) allows developers to build, deploy, and optimize AI agents, manage prompts, and evaluate generative AI models.

  • Project
    muratcankoylan/Agent-Skills-for-Context-Engineering

    A collection of platform-agnostic Agent Skills focused on context engineering to optimize how AI agents manage their limited attention budget and context windows.

  • Project
    samber/cc-skills-golang

    A curated set of AI‑agent “skills” that encode Go best‑practice guidance (style, testing, concurrency, libraries, etc.). Installable via the universal `skills` CLI or by cloning into the discovery folder of Claude Code, Copilot, Gemini, Cursor, etc. Skills are atomic, human‑reviewed, and dramatically improve AI‑assistant accuracy on Go code reviews.