skills.rest
robomotionio
robomotionioOFFICIAL
Explore all skills by this author →
Website𝕏@robomotionioGitHub

gemini-ai

Automate Gemini text generation, image analysis, and embeddings via the robomotion googlegemini CLI.

2|1|Updated Mar 13, 2026
Search Tags:#embeddings#vision#gemini#google#chat#text-generation
One-click install
npx skills add https://github.com/robomotionio/robomotion-skills --skill gemini-ai-robomotionio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-ai
Source: https://github.com/robomotionio/robomotion-skills/tree/main/skills/gemini-ai
Command: npx skills add https://github.com/robomotionio/robomotion-skills --skill gemini-ai-robomotionio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Gemini-based generation, vision analysis, and embedding creation enable end-to-end AI interactions within Robomotion workflows, consolidating multi-modal capabilities behind a single CLI.

Core Features & Use Cases

  • Text generation with Google Gemini models
  • Image analysis and description from prompts
  • Embedding generation for semantic search and similarity
  • Multi-turn chat with history and session management
  • Content generation and vision-enabled prompts for documents and media

Quick Start

Connect with robomotion googlegemini, establish a session, and begin generating or chatting with Gemini using the provided commands.

Frequently Asked Questions about gemini-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate text generation and image analysis using Google Gemini models?▼

Automate text generation and image analysis using Google Gemini models through the robomotion googlegemini CLI, which handles multi-modal content generation, vision-enabled prompts, and single-turn outputs within Robomotion workflows.

Can I maintain multi-turn chat history with Google Gemini inside an automated workflow?▼

Yes, you can maintain multi-turn chat history with Google Gemini by establishing a session using a session-id, allowing subsequent commands to preserve context for long-running conversational interactions.

How do I generate embeddings for semantic search pipelines with Google Gemini?▼

Generate embeddings for semantic search pipelines by passing text and image data through the googlegemini CLI, producing vector representations that enable similarity matching across your content.

Do I need a specific environment setup to run Google Gemini commands in Robomotion?▼

You need the Robomotion CLI installed locally, a Google Gemini API key configured in the vault, and proper session handling with connect and session-id commands to execute subsequent Gemini operations.

What is the best way to consolidate multi-modal AI capabilities behind a single CLI?▼

Consolidate multi-modal AI capabilities behind a single CLI by using the googlegemini interface, which unifies text generation, vision analysis, and embedding creation under one command structure for streamlined workflow automation.

Why should I use Google Gemini for vision-enabled prompts on documents and media?▼

Use Google Gemini for vision-enabled prompts to analyze and describe images from prompts, enabling automated extraction of visual information from documents and media files within your pipelines.

Related Skills

Explore More Software Engineering Skills→
robomotioniorobomotionio
2

serper

Query the Serper API for structured Google search results in JSON.

Official
Advanced
jcolanojcolano

zeppelin

Store and retrieve text as 384-dimensional semantic vectors for similarity search.

Community
Advanced
robomotioniorobomotionio
2

millionverifier

Verify email addresses via MillionVerifier within Robomotion sessions.

Official
Intermediate
founderphantomfounderphantom

clip

Connects images and text for zero-shot classification and cross-modal retrieval.

Community
Intermediate