← Back to Skills Marketplace
Nano Banana Pro 1.0.1
by
Guogithubname
· GitHub ↗
· v1.0.0
· MIT-0
157
Downloads
0
Stars
14
Active Installs
1
Versions
Install in OpenClaw
/install nano-banana-pro-1-0-1
Description
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K...
Usage Guidance
This skill appears to do what it claims (image generation via Google Gemini), but there are configuration and provenance issues you should address before installing or using it: 1) The runtime requires a Gemini API key (GEMINI_API_KEY) and the 'uv' runner, but those are not declared in the registry metadata — treat this as a packaging/metadata bug. 2) Do not paste your API key into a chat to provide --api-key; prefer setting GEMINI_API_KEY locally in a secure environment. 3) The ownerId in _meta.json differs from the registry Owner ID — verify the skill's source and author (no homepage provided). 4) If you proceed, run the script in an isolated environment, confirm the google-genai/pillow dependencies come from trusted registries, and consider setting least-privilege API keys (limited scope/quota) for testing. If the author cannot explain the metadata omissions and owner mismatch, prefer not to install.
Capability Assessment
Purpose & Capability
The name, description, SKILL.md, and script all describe an image-generation/editing skill using Google's Gemini (genai) API — this is coherent. However, the skill registry declares no required credentials or binaries while the runtime actually needs an API key (GEMINI_API_KEY or --api-key) and the 'uv' runner. The package metadata ownerId in _meta.json does not match the registry Owner ID, which is a red flag about provenance or bundling.
Instruction Scope
The SKILL.md instructions are narrowly scoped to generating or editing images: they describe how to run the script, how to pass prompts/filenames, resolution mapping, and basic preflight checks (uv exists, API key present, input image file exists). The script only reads the provided input image path (if any) and the GEMINI_API_KEY env var; it does not attempt to read unrelated files or system configuration.
Install Mechanism
There is no install spec (instruction-only skill with one local script). The Python script lists dependencies in comments (google-genai, pillow) but does not download anything at install time. No external, arbitrary download URLs or extract operations are present.
Credentials
The script requires an API key (GEMINI_API_KEY or passed via --api-key) to function, but the registry metadata declares no required environment variables or primary credential. Additionally, the SKILL.md expects the 'uv' runner but the registry lists no required binaries. These omissions are disproportionate to the declared metadata and increase the risk of accidental misuse (for example users pasting API keys into chat to supply --api-key).
Persistence & Privilege
The skill does not request persistent/always-on privileges (always:false), does not modify other skills or global agent configuration, and has no special OS restrictions. Autonomous invocation is allowed but is the platform default and not by itself a concern.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install nano-banana-pro-1-0-1 - After installation, invoke the skill by name or use
/nano-banana-pro-1-0-1 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of nano-banana-pro skill, enabling image generation and editing via Google’s Gemini 3 Pro Image API.
- Supports both text-to-image and image-to-image workflows, including prompt-based edits.
- Handles 1K, 2K, and 4K resolution options with user-friendly resolution mapping.
- Saves images in the current working directory using timestamped, descriptive filenames.
- Flexible API key management (argument or environment variable).
- Includes preflight checks, error handling guidance, and prompt templates for both generation and editing use cases.
Metadata
Frequently Asked Questions
What is Nano Banana Pro 1.0.1?
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K... It is an AI Agent Skill for Claude Code / OpenClaw, with 157 downloads so far.
How do I install Nano Banana Pro 1.0.1?
Run "/install nano-banana-pro-1-0-1" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Nano Banana Pro 1.0.1 free?
Yes, Nano Banana Pro 1.0.1 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Nano Banana Pro 1.0.1 support?
Nano Banana Pro 1.0.1 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Nano Banana Pro 1.0.1?
It is built and maintained by Guogithubname (@guogithubname); the current version is v1.0.0.
More Skills