← 返回 Skills 市场
Nano Banana Pro
作者
DyCathecorde
· GitHub ↗
· v0.1.0
5630
总下载
18
收藏
17
当前安装
1
版本数
在 OpenClaw 中安装
/install nano-banana-pro-2
功能描述
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
安全使用建议
Install only if you are comfortable sending the prompt and any selected input images to Google Gemini and using your Gemini API quota. Prefer a dedicated or limited API key stored in the environment rather than passed on the command line, avoid sensitive images unless allowed by your data policy, and review uv-resolved Python dependencies if supply-chain control matters.
功能分析
Type: OpenClaw Skill
Name: nano-banana-pro-2
Version: 0.1.0
The skill is designed to generate or edit images using the Google Gemini 3 Pro Image API. It correctly handles API keys from environment variables or command-line arguments, reads user-specified input image files, and writes the generated/edited image to a user-specified output path. All file system and network operations are directly aligned with the stated purpose of image generation/editing. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts against the agent, or obfuscation. The dependencies are standard for the functionality provided.
能力评估
Purpose & Capability
The stated purpose is image generation/editing via Gemini 3 Pro Image, and the script directly implements that by calling google-genai with the user's prompt and optional input images.
Instruction Scope
Runtime instructions are limited to explicit CLI examples for generation, editing, and composition; there is no hidden autonomous workflow, prompt override, obfuscation, or unrelated tool use.
Install Mechanism
The skill requires uv and declares runtime Python dependencies google-genai and pillow; this is proportionate, but users with strict supply-chain needs should review or pin dependencies.
Credentials
It uses a Gemini API key, reads only user-specified input image paths, writes the requested output file, and sends prompt/image content to Google's service as expected for this function.
Persistence & Privilege
No background service, cron job, privilege escalation, destructive action, or credential harvesting is shown; persistence is limited to creating parent directories and saving the generated image.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install nano-banana-pro-2 - 安装完成后，直接呼叫该 Skill 的名称或使用
/nano-banana-pro-2触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
Initial release of Nano Banana Pro (Gemini 3 Pro Image) skill.
- Generate or edit images using Gemini 3 Pro via a bundled Python script.
- Supports image generation, editing a single image, and composing up to 14 images.
- Choose output resolution: 1K (default), 2K, or 4K.
- Requires a GEMINI_API_KEY environment variable.
- Outputs saved image path and a special MEDIA: line for chat integration.
- Installation instructions provided for dependencies (uses uv).
元数据
常见问题
Nano Banana Pro 是什么？
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 5630 次。
如何安装 Nano Banana Pro？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nano-banana-pro-2」即可一键安装，无需额外配置。
Nano Banana Pro 是免费的吗？
是的，Nano Banana Pro 完全免费（开源免费），可自由下载、安装和使用。
Nano Banana Pro 支持哪些平台？
Nano Banana Pro 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Nano Banana Pro？
由 DyCathecorde（@dycathecorde）开发并维护，当前版本 v0.1.0。
推荐 Skills