gemini▌

Multimodal AI with Gemini 2.5 and 3 models, supporting text, images, video, audio, PDFs, function calling, thinking mode, and real-time web grounding. \n \n Supports three deployment approaches: Node.js SDK (@google/genai), fetch-based REST API for edge runtimes, and chat helpers for multi-turn conversations \n Handles multimodal inputs (images, video, audio, PDFs) with 1,048,576 token context window; thinking mode enabled by default for enhanced reasoning quality \n Includes function calling wi

Gemini 2.5 Computer Use browser automation with Playwright-based agent loops and safety confirmations. \n \n Implements a screenshot-to-action cycle: capture screen, send to Gemini, parse function calls, execute in Playwright, return results until task completion or turn limit \n Supports multiple browser options: bundled Chromium (default), Chrome/Edge channels via COMPUTER_USE_BROWSER_CHANNEL , or custom executables like Brave \n Includes safety confirmation workflow that prompts users before

Unified interface for Gemini models and agents with server-side state, streaming, and tool orchestration. \n \n Supports multiple current models (gemini-3-flash-preview, gemini-3-pro-preview, gemini-2.5-flash/pro) and the Deep Research agent; automatically substitute deprecated model IDs with current alternatives \n Offload conversation history to the server via previous_interaction_id for stateful multi-turn interactions without manual history management \n Built-in tool orchestration including

Remove visible Gemini AI watermarks from images using reverse alpha blending. \n \n Provides a Python CLI tool that strips the bottom-right Gemini watermark without requiring HTML or server-side components \n Uses pre-captured watermark alpha maps (48px and 96px variants) and reverse alpha blending to reconstruct the underlying image \n Supports any image format that Pillow can read and write, with output format inferred from file extension \n Includes detailed algorithm documentation covering d

Build applications with Google's Gemini models, supporting multimodal content, function calling, and structured outputs across Python, JavaScript, Go, and Java. \n \n Access current Gemini 3 models (Pro, Flash, Pro Image) with 1M token context; legacy Gemini 2.x and 1.5 models are deprecated \n Supports text generation, image/audio/video understanding, function calling, structured JSON output, code execution, context caching, and embeddings \n Official SDKs available: google-genai (Python), @goo

Look up Gemini API documentation and SDK patterns when building with Google Gemini. This skill brings Gemini docs TO Claude — it does not call Gemini.

Consult Gemini as a coding peer for a second opinion on code quality, architecture decisions, debugging, or security reviews.

Comprehensive code review and large-context analysis using Gemini 3 Pro with flexible approval modes. \n \n Supports five Gemini models ranging from flagship reasoning (Gemini 3 Pro) to cost-optimized alternatives, with 1M token input windows for analyzing entire codebases and documentation sets \n Three approval modes: default for interactive terminal prompts, auto_edit for auto-approving code suggestions, and yolo for fully automated background execution \n Critical safety requirement: use --a