AI Skills for Google Gemini

Facilitates autonomous multi-step research using Google Gemini for market analysis, competitive landscaping, and technical reviews.

Facilitates application development using Gemini API for multimodal content, function calling, and structured outputs.

Generates images using Google Gemini for UI placeholders, documentation, and design assets, enhancing visual content creation.

Generates and edits images using Google's Nano Banana Pro API, supporting text-to-image and image-to-image modifications.

Automates web browser tasks using Gemini 2.5 and Playwright, enabling users to build and run browser-control agents efficiently.

Automatically routes tasks to the best AI model based on type and cost, optimizing performance across multiple providers.

Generates and stitches short videos using Google Veo 3.x and the Gemini API for ads and product demos with a reproducible CLI workflow.

Optimizes AI model usage and reduces costs with dynamic compaction and intelligent file management for various AI models.

Generates and stitches short videos using Google Veo 3.x and the Gemini API for ads and product demos with a CLI workflow.

Routes tasks to the optimal AI model across multiple providers, enhancing efficiency in AI model utilization.

Analyzes videos using Google Gemini API to extract insights, summarize content, and identify objects and actions within the footage.

TruthCheck verifies claims, checks URL trustworthiness, and traces misinformation origins using a powerful CLI tool.

Generates high-quality academic diagrams and statistical plots from text descriptions using a multi-agent AI pipeline.

Generates AI-powered short videos from topics or reference videos, perfect for social media and e-commerce content creation.

Generates a clean, verbatim transcript of YouTube videos using Google Gemini, formatted with speaker labels and paragraph breaks.

Builds RAG pipelines for enhanced research and fact-checking using web search and LLMs, ensuring accurate and grounded AI responses.

Enables real-time web searches via the Gemini API for grounded, citable answers to user queries.

Conducts deep research using the Perplexity Agent API for comprehensive analysis, market insights, and trend evaluations.

Generates and edits images using the Google Gemini API through the nanobanana tool, offering customizable options for output.

Manages coding agents in tmux sessions for efficient background tasks, allowing simultaneous coding and monitoring of progress.