Access Google Gemini models with function calling and structured outputs.
npx skills add https://github.com/eco2-team/backend --skill gemini-sdk
Please help me install this Agent Skill. Skill: gemini-sdk Source: https://github.com/eco2-team/backend/tree/main/.claude/skills/gemini-sdk Command: npx skills add https://github.com/eco2-team/backend --skill gemini-sdk
This Skill provides a practical guide to using the Google Gemini SDK (google-genai) to access Gemini models, enable structured outputs, function calling, Google Search grounding, and image generation capabilities.
Install the google-genai package via pip and initialize a client with your API key. Example:
from google import genai client = genai.Client(api_key="GOOGLE_API_KEY")
import os client = genai.Client(api_key=os.environ["GOOGLE_API_KEY"])
High-intent search queries and answers about installing and using this skill.
Use the google-genai library to access Gemini models and enable structured outputs and function calling for building composable AI applications. You initialize a client with your API key, then configure requests to return structured data or route to defined functions.
Google Search grounding allows Gemini models to retrieve real-time web information during generation. By enabling this feature in the Gemini SDK, your AI workflows access current data, ensuring responses are factually grounded in live search results.
Yes, the Gemini SDK supports image generation capabilities using models like gemini-3-pro and gemini-2.0 variants. You can request image generation and receive inline image results directly within your Python application workflow.
Yes, you need to install the google-genai Python package and provide a Google API key. You can initialize the client by passing the API key directly or loading it from an environment variable to access Gemini models.
The SDK provides programmatic access to Gemini models including gemini-3-pro, gemini-3-flash, and gemini-2.0/1.5 variants. These models support features like structured outputs, function calling, and live web grounding.
dfpalhanoExecute Google Search within Gemini models for grounded, cited answers.
pradyumnasagarAutomate inter-skill data transfer and provenance capture via JSON Material Passports.
BoraPerusicIntegrate Google Gemini API for multimodal inputs, streaming, and function calling.
pradyumnasagarGuide authors through creating and validating ORS SKILL.md files.
