← 返回 Skills 市场
350
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install nano-banana-2-image-gen
功能描述
图片生成技能，当用户需要生成图片、视觉信息图、创建图像、编辑/修改/调整已有图片时使用此技能。基于中国的API易代理站(https://api.apiyi.com/)的NanoBanana2模型的图片生成服务，无需访问外网。支持14种宽高比的图片比例（`1:1`、`16:9`、`9:16`、`4:3`、`3:4`...
安全使用建议
Before installing or using this skill: (1) Be aware it WILL upload your prompt text and any input images (base64) to api.apiyi.com — do not provide sensitive images or prompts you don't want transmitted. (2) The skill requires an API key (APIYI_API_KEY or --api-key) but the registry metadata incorrectly listed no required env vars; expect to provide and protect that key. (3) Verify you trust api.apiyi.com and understand their privacy/retention policies. (4) If you need stronger guarantees (no external upload), do not use this skill. (5) Prefer running the provided scripts locally and inspect them (they are small and readable); confirm the API endpoint and key handling meet your policy before giving the key to the environment.
功能分析
Type: OpenClaw Skill
Name: nano-banana-2-image-gen
Version: 0.1.1
The skill bundle provides image generation and editing capabilities using the Gemini 3.1 Flash model via a third-party API proxy (api.apiyi.com). The included Node.js and Python scripts (generate_image.js and generate_image.py) implement standard API interaction logic, including base64 encoding for image-to-image tasks and local file writing for results. No evidence of malicious behavior, data exfiltration, or harmful prompt injection was found; the code is transparent and aligns with its stated purpose.
能力标签
能力评估
Purpose & Capability
The name/description (image generation via NanoBanana2 on api.apiyi.com) match the included scripts and instructions. However the registry metadata lists no required environment variables or primary credential, while SKILL.md and both scripts clearly require an API key (APIYI_API_KEY or --api-key). That metadata mismatch is incoherent and could mislead users about what secrets they must provide.
Instruction Scope
SKILL.md and the scripts are consistent: they take a prompt and optional input images, base64-encode images and POST a JSON payload to https://api.apiyi.com/...generateContent. The instructions do not attempt to read unrelated system paths or other credentials. Important operational behavior: user prompts and any input images (encoded as base64) are transmitted to an external API service — this is expected for an image-editing/generation skill but has privacy/security implications that are not emphasized in the registry metadata.
Install Mechanism
No install spec or remote downloads are present; this is an instruction-only skill with included Python/Node scripts. Nothing in the files attempts to fetch or execute arbitrary third-party code during install.
Credentials
The code requires an API key (APIYI_API_KEY or command-line -k) to call the api.apiyi.com service. The skill registry, however, declared 'Required env vars: none' and 'Primary credential: none' — that contradicts the actual need to supply a secret. The requested credential (single API key) is proportional to the stated purpose, but the metadata omission is misleading.
Persistence & Privilege
The skill does not request persistent presence (always: false). It does not modify other skills or system-wide settings. Autonomous invocation is allowed by default (disable-model-invocation: false) which is normal for skills; this combined with the metadata mismatch raises no new privilege concerns beyond the usual caution about granting API keys.
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-2-image-gen - 安装完成后，直接呼叫该 Skill 的名称或使用
/nano-banana-2-image-gen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
v0.1.1
nano-banana-2-image-gen v0.1.1
- 修正了服务描述中的API易官网地址，由 https://apiyi.com/ 更新为 https://api.apiyi.com/
- 其余说明、功能与使用方式保持不变
v0.1.0
Initial release of nano-banana-2-image-gen, an image generation and editing skill based on Google's NanoBanana2 model, accessible via API易中国代理。
- Supports both text-to-image and image-to-image (editing) via domestic API proxy; no external Internet required.
- Offers 14 aspect ratio options (such as 1:1, 16:9, 9:16, etc.) and 3 resolutions (1K, 2K, 4K), with 2K as default.
- Keeps user input as-is for prompts, asking clarifying questions before appending extra details.
- Runs via Node.js (preferred, zero-dependency) or Python command-line scripts; fallbacks handled automatically.
- Guides users on environment setup and API key management, with detailed usage examples and error handling.
- Includes clear documentation for typical scenarios, parameters, and best practices.
元数据
常见问题
Nano Banana 2 Image Gen(基于API易代理站) 是什么？
图片生成技能，当用户需要生成图片、视觉信息图、创建图像、编辑/修改/调整已有图片时使用此技能。基于中国的API易代理站(https://api.apiyi.com/)的NanoBanana2模型的图片生成服务，无需访问外网。支持14种宽高比的图片比例（`1:1`、`16:9`、`9:16`、`4:3`、`3:4`... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 350 次。
如何安装 Nano Banana 2 Image Gen(基于API易代理站)？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nano-banana-2-image-gen」即可一键安装，无需额外配置。
Nano Banana 2 Image Gen(基于API易代理站) 是免费的吗？
是的，Nano Banana 2 Image Gen(基于API易代理站) 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Nano Banana 2 Image Gen(基于API易代理站) 支持哪些平台？
Nano Banana 2 Image Gen(基于API易代理站) 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 2 Image Gen(基于API易代理站)？
由 无处不在（@wuchubuzai2018）开发并维护，当前版本 v0.1.1。
推荐 Skills