← Back to Skills Marketplace
Nano Banana Pro Cn
by
onlyloveher
· GitHub ↗
· v1.0.0
· MIT-0
95
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install nano-banana-v1
Description
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://apiyi.com/)的NanoBananaPro模型的图片生成服务，无需访问外网。支持10种宽高比的图片比例（`1:1`、`16:9`、`9:16`、`4:3`、`3:4`、`...
Usage Guidance
Before installing: 1) Be aware this skill will upload your prompts and any input images (converted to base64) to https://api.apiyi.com — do NOT use it with sensitive/private images or data unless you trust that service and its privacy policy. 2) The registry metadata incorrectly indicates 'no required env vars' but the code and SKILL.md require an API key (APIYI_API_KEY or --api-key). Treat the API key as a secret and confirm where/how you store it. 3) The skill files are local scripts (Node/Python); review their network endpoint (api.apiyi.com) and the code if you have doubts. 4) Notice small inconsistencies in package metadata (_meta.json ownerId differs from registry owner and skill.yaml author/homepage); these can indicate sloppy packaging — prefer skills with clear provenance. 5) If you must use it, create and scope an API key just for this purpose, avoid sending sensitive inputs, and consider testing in an isolated environment first.
Capability Analysis
Type: OpenClaw Skill
Name: nano-banana-v1
Version: 1.0.0
The skill bundle provides image generation and editing capabilities by interfacing with a third-party API proxy (apiyi.com). The implementation in both scripts/generate_image.js and scripts/generate_image.py is transparent, focusing on encoding user-provided images to base64 and communicating with the specified API endpoint. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection; the instructions in SKILL.md are strictly operational and aligned with the stated purpose.
Capability Assessment
Purpose & Capability
The skill's name/description (image generation) aligns with the JS/Python scripts and SKILL.md. However registry metadata declared no required environment variables or credentials while SKILL.md, both scripts, and skill.yaml all require an API key (APIYI_API_KEY / API_KEY). This metadata mismatch is incoherent and should be corrected before trusting automatic installs.
Instruction Scope
Runtime instructions explicitly read local image files (encode them to base64) and POST prompts + image data to https://api.apiyi.com. That behavior is consistent with the stated purpose, but SKILL.md/description includes wording like “无需访问外网” which contradicts the actual network calls to api.apiyi.com. The instructions otherwise do not request unrelated system files or credentials beyond the API key.
Install Mechanism
There is no install spec (instruction-only installation). The package includes two local scripts (Node and Python) but does not download or execute additional remote code during install. This is lower risk compared to remote downloads.
Credentials
Only one secret is actually required (an API key for api.apiyi.com), which is proportionate for a remote image-generation service. The concern is that registry metadata falsely lists no required env vars while the scripts and SKILL.md require APIYI_API_KEY / support --api-key. That mismatch could mislead users into installing without providing or protecting the key.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide configuration, and does not persist extra privileged access. It only reads local image files when the user provides them and writes generated images to the output path.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install nano-banana-v1 - After installation, invoke the skill by name or use
/nano-banana-v1 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
nano-banana-v1 1.0.0
- Initial release of the nano-banana-pro-cn skill for AI-powered image generation and editing via the API易代理服务 (China-based NanoBananaPro model).
- Supports both text-to-image and image-to-image workflows, including advanced editing capabilities.
- Offers 10 aspect ratios (e.g., 1:1, 16:9, 9:16) and 3 resolutions (1K, 2K, 4K); defaults favor 2K.
- Provides detailed command-line usage for both Node.js and Python environments, including fallback strategies.
- Enforces preservation of users’ original prompt text, with a clear process for confirming and appending additional details.
- Includes full documentation for setup, API key management, and operational best practices.
Metadata
Frequently Asked Questions
What is Nano Banana Pro Cn?
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://apiyi.com/)的NanoBananaPro模型的图片生成服务，无需访问外网。支持10种宽高比的图片比例（`1:1`、`16:9`、`9:16`、`4:3`、`3:4`、`... It is an AI Agent Skill for Claude Code / OpenClaw, with 95 downloads so far.
How do I install Nano Banana Pro Cn?
Run "/install nano-banana-v1" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Nano Banana Pro Cn free?
Yes, Nano Banana Pro Cn is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Nano Banana Pro Cn support?
Nano Banana Pro Cn is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Nano Banana Pro Cn?
It is built and maintained by onlyloveher (@onlyloveher); the current version is v1.0.0.
More Skills