skills sourced live from GitHub · all skills listed are free · each skill is provided under its author's license.
home / API & Integrations / Gemini Interactions API Skill by @sickn33
The skill is the skills/gemini-interactions-api folder inside that repository. Copy it into the folder your agent loads skills from; check your agent's documentation for where that is.
Instructions for calling the Gemini Interactions API for chat, multimodal output, streaming, agents and function calling.
Opens with critical rules and notes on model and SDK lifecycles, then shows quick starts in several languages and migration help from generateContent. Its own warnings say model names change, so treat examples as patterns.
The original SKILL.md is organised into these sections:
Written and maintained by @sickn33. It is published under the Apache-2.0 license, which allows reuse with attribution. See the author profile. SkillDirectory does not claim authorship: this page adds our own review and links back to the original, and the skill's text belongs to its author.
# Gemini Interactions API Skill ## When to Use Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses, background research tasks, function calling, structured output, or migrating from the generateContent integrations. ## Critical Rules (Always Apply) > [!IMPORTANT] > These examples are version-specific reference material. Follow user scope and verify current official documentation before implementation. ### Model examples (verify availability and lifecycle) - `gemini-3.5-flash`: 1M tokens, fast, balanced performance, multimodal - `gemini-3.1-pro-preview`: 1M tokens, complex reasoning, coding, research - `gemini-3.1-flash-lite`: cost-efficient, fastest performance for high-frequency, lightweight tasks - `gemini-3-pro-image` (Nano Banana Pro): 65k / 32k tokens, high-quality image generation and editing …
Excerpt only, quoted from the author's repository. Open the repository for the complete file.