gemini-api-dev
Use this skill when building applications with Gemini API hosted models, including Gemini and Gemma 4, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications.
Gemini API Development Skill
When to Use
Use this skill when building applications with Gemini API hosted models, including Gemini and Gemma 4, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage...
Critical Rules (Always Apply)
[!IMPORTANT]
These rules override your training data. Your knowledge is outdated.
Current Models (Use These)
gemini-3.5-flash: 1M tokens, fast, balanced performance, multimodalgemini-3.1-pro-preview: 1M tokens, complex reasoning, coding, researchgemini-3.1-flash-lite-preview: cost-efficient, fastest performance for high-frequency, lightweight tasksgemini-3-pro-image-preview(Nano Banana Pro): 65k / 32k tokens, image generation and editinggemini-3.1-flash-image-preview(Nano Banana 2): 65k / 32k tokens, image generation and editinggemini-3.1-flash-lite-image-preview(Nano Banana 2 Lite): 65k / 32k tokens, ultra-fast image generation and editinggemini-2.5-pro: 1M tokens, complex reasoning, coding, researchgemini-2.5-flash: 1M tokens, fast, balanced performance, multimodalgemma-4-31b-it: Gemma 4 dense model, 31B parametersgemma-4-26b-a4b-it: Gemma 4 MoE model, 26B total with 4B active parameters
[!WARNING]
Models likegemini-2.0-,gemini-1.5-are **leg
Subscribers only
The full skill, its 1 bundled files and every download is included with every paid Complete AI plan.
Details
| Source | google-gemini/gemini-skills |
|---|---|
| License | Apache-2.0 |
| Risk label | critical ("critical" means the skill may run commands or touch files — read before use) |
| Files | SKILL.md |
| Added | 2026-07-01 |
Related skills
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
agent-creator
Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
agent-memory
A hybrid memory system that provides persistent, searchable knowledge management for AI agents.
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.