“Gemini”

Grounded Google Search, URL reading, and gated Deep Research via Gemini (GEMINI_API_KEY).

Use this skill when users ask to generate, edit, or compose images with Gemini Nano Banana 2, including text-to-image, image editing, multi-image composition…

Use this skill when a user provides a web page URL, PDF file, video, or audio file and wants a Traditional Chinese summary.

Use this skill when the user wants to generate music or audio tracks from lyrics or text prompts using Gemini Lyria-3, including AI music composition, audio…

Use this skill when a user wants a comprehensive research report on any topic with cited sources.

Delegate a sub-task to Gemini CLI via the Agent Client Protocol (ACP).

Remove visible Gemini image watermarks from local image files.

Use this skill when a user provides an audio file (local file or URL) and wants it transcribed into Traditional Chinese text.

Use this skill when a user provides an image (local file or URL) and wants a detailed Traditional Chinese description of the image content.

Delegate a sub-task to Claude Code via the Agent Client Protocol (ACP).

Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API.

Persistent per-project memory for Gemini CLI.

Generates illustrations and photos with an AI image provider (Gemini or OpenAI) after the person approves the cost, and marks every result as AI-generated.

Persistent per-project memory for Gemini Code.

从 10,000+ Nano Banana Pro 图像生成提示词中推荐合适的提示词，基于用户需求进行推荐。 针对 Nano Banana Pro (Gemini) 优化，但提示词同样适用于 Nano Banana 2、Seedream 5.0、 GPT Image…

“Multi-model dispatcher -- sends a task or prompt to other AI models (Codex / Gemini / Kimi / DeepSeek / Doubao / Qwen / GLM / MiniMax) and retrieves results.

Use this skill if the user asks you to help them address GitHub PR comments for their current branch of the Gemini CLI.

SpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your…

How a Claude subagent runs Google Antigravity (agy, Gemini) headless as a background job and relays its answer.

【通用版】当用户发来文件（PDF/Word/文本）时：提取正文、总结要点、保留原文供追问。纯流程型，不带代码，无环境依赖，任何 AI 助手（ChatGPT / Gemini / Claude / Codex……）都能用。

Generate images using the internal Google Antigravity API (Gemini 3 Pro Image).

Resolves open GitHub Issues in parallel by fanning out independent subagents and then fanning in to aggregate lessons learned.

AI-generated visual presentations with full-bleed Gemini images.

Cross-agent messaging via SQLite.