gemini-llm

Solid

Invoke Google Gemini 3 Pro for text generation, reasoning, and code tasks using the Python google-genai SDK. Supports gemini-3-pro-preview (best multimodal), gemini-2.5-pro (reasoning), and gemini-2.5-flash (fast).

AI & Automation 364 stars 68 forks Updated today MIT

Install

View on GitHub

Quality Score: 89/100

Stars 20%
85
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Gemini LLM Skill Invoke Google Gemini models for text generation, reasoning, code analysis, and complex tasks using the Python `google-genai` SDK. ## Available Models | Model ID | Description | Best For | |----------|-------------|----------| | `gemini-3-pro-preview` | Best multimodal understanding | Complex reasoning, analysis | | `gemini-2.5-pro` | Advanced thinking model | Deep reasoning, planning | | `gemini-2.5-flash` | Fast and capable | Quick tasks, high throughput | | `gemini-2.5-flash-lite` | Fastest, cost-efficient | Simple tasks, bulk processing | ## Configuration **API Key Location**: `C:\Users\USERNAME\env` (GEMINI_API_KEY) **Default API Key**: `${GEMINI_API_KEY}` ## Usage ### Basic Text Generation ```bash python -c " from google import genai client = genai.Client(api_key=os.environ.get("GEMINI_API_KEY")) response = client.models.generate_content( model='gemini-3-pro-preview', contents='YOUR_PROMPT_HERE' ) print(response.text) " ``` ### With System Instructions ```bash python -c " from google import genai from google.genai import types client = genai.Client(api_key=os.environ.get("GEMINI_API_KEY")) response = client.models.generate_content( model='gemini-3-pro-preview', contents='YOUR_PROMPT_HERE', config=types.GenerateContentConfig( system_instruction='You are a helpful coding assistant.', temperature=0.7, max_output_tokens=8192 ) ) print(response.text) " ``` ### Streaming Response ```bash python -c...

Details

Author
majiayu000
Repository
majiayu000/claude-skill-registry
Created
5 months ago
Last Updated
today
Language
HTML
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category