gemini-prompting

# Gemini Prompt Engineering

Gemini is Google's multimodal AI model designed from the ground up for text, images, audio, video, and code. It features system instructions, ultra-long context windows (up to 1M+ tokens), and native multimodal understanding.

## When to Invoke This Skill

Use this skill when:
- Crafting prompts specifically for Gemini/Google models
- Using system instructions to guide behavior
- Working with multimodal inputs (text, images, video, audio)
- Leveraging ultra-long context (1M+ tokens)
- Building with Gemini's agent reasoning capabilities

## Gemini's Identity & Characteristics

| Attribute | Description |
|-----------|-------------|
| **Architecture** | Multimodal-first (text, images, audio, video, code) |
| **Context Window** | Up to 1M+ tokens (industry-leading) |
| **System Instructions** | Primary feature for behavior control |
| **Strengths** | Multimodal reasoning, long-context, code generation |
| **Prompt Style** | Flexible with system instruction preference |
| **Models** | Gemini 3 Flash (fast), Gemini 3 Pro (capable), Gemini 2.5 Flash/Pro (legacy) |

## Universal Prompting Techniques (Gemini-Adapted)

### 1. Zero-Shot Prompting with System Instructions

Gemini's system instructions are powerful for zero-shot tasks.

```json
{
  "system_instruction": {
    "parts": [{"text": "You are a technical writing assistant. Your responses are clear, concise, and use Markdown formatting."}]
  },
  "contents": [{"parts": [{"text": "Explain how JWT authentication works."}]}]
}
```

### 2. Few-Shot Prompting

```xml
<system_instruction>
You are a sentiment classifier. Categorize text as positive, negative, or neutral.
</system_instruction>

<examples>
<example>
<input>
I absolutely love this product! Best purchase I've made all year.
</input>
<output>
{"sentiment": "positive", "confidence": 0.95}
</output>
</example>

<example>
<input>
This is the worst customer service I've ever experienced.
</input>
<output>
{"sentiment": "negative", "confid