Skills

Enables interaction with Google's Gemini AI model, providing advanced language generation and multi-modal capabilities within the AgentStack framework.

Generates and analyzes text, images, and code using Google's advanced multimodal AI model with flexible prompting capabilities

Delegates tasks to Google Gemini 3 series models, leveraging multimodal capabilities for text, vision, and image generation/editing.

Efficiently process large volumes of AI requests using Gemini Batch API, enabling cost-effective bulk text generation and async job execution via scripts.

Generates comprehensive CLI documentation documentation for the Gemoinini-by extracting and formatting reference details from the source code and command specifications.

Executes Google Gemini CLI commands and interactions directly through Claude Code, enabling streamlined AI model command-line operations.

Enables rapid development and management of command-line interfaces for Google Gemini AI integration, providing scaffolding and tooling for CLI tool creation.

Manages and synchronizes configuration settings for Google Gemini AI services across different development environments and project configurations.

Enables advanced delegation and interaction patterns between Claude and Google's Gemini AI, facilitating cross-platform AI task coordination and workflow optimization.

Generates high-quality text embeddings using Gemini API for semantic search, similarity analysis, clustering, and RAG applications.

Explores and generates design patterns and architectural strategies specifically tailored for Google's Gemini AI models and ecosystem.

Helps developers rapidly prototype, scaffold, and, generate boilerplate code for for Chrome browser extensions using Google Google's Gem/ini AI.