← Back to Skills Marketplace
568
Downloads
0
Stars
3
Active Installs
2
Versions
Install in OpenClaw
/install nano-banana-2-direct
Description
Generate/edit images with Gemini 3.1 Flash Image Preview (Nano Banana 2). Direct API call without inference.sh dependency. Use for image create/modify reques...
Usage Guidance
This skill appears to do what it says: it sends prompts and optional input images to Google's Gemini image model and saves the returned PNG. Before installing: (1) ensure you want to provide a GEMINI_API_KEY to this code; (2) review/confirm the 'google-genai' package source (pip install will run remote code)—use a virtualenv; (3) don't pass sensitive images or credentials as input-image or in prompts, since data goes to Google's API; and (4) verify you have the 'uv' runner available and are comfortable running the included script from your current working directory.
Capability Analysis
Type: OpenClaw Skill
Name: nano-banana-2-direct
Version: 1.0.1
The skill is a legitimate tool for generating and editing images using the Google Gemini 3.1 Flash Image API. The Python script (scripts/generate_image.py) uses standard libraries (google-genai, pillow) to handle API requests and image processing, with no evidence of data exfiltration, malicious execution, or obfuscation. The instructions in SKILL.md are well-aligned with the stated purpose and do not contain any harmful prompt-injection attempts.
Capability Assessment
Purpose & Capability
Name/description (Gemini image generation) match the actual footprint: it needs GEMINI_API_KEY, the 'uv' runner, and installs google-genai + pillow to call Google's GenAI image model. These requirements are appropriate and expected.
Instruction Scope
SKILL.md instructs running the included script via 'uv run', provides preflight checks, handles input-image paths, and saves output PNGs to the current working directory. Instructions do not ask the agent to read unrelated files, secrets, or send data to third-party endpoints beyond the Gemini API client.
Install Mechanism
There is no aggressive installer; the metadata recommends running 'uv pip install google-genai pillow'. Installing PyPI packages is normal for a Python script but will execute code from those packages—verify you trust the 'google-genai' package source and consider using a virtual environment.
Credentials
Only GEMINI_API_KEY is required (and optionally provided as a CLI flag). No unrelated credentials, config paths, or broad environment access are requested.
Persistence & Privilege
The skill does not request always:true, does not persist or modify other skills, and is user-invocable. It can be invoked autonomously per platform defaults but has no elevated persistence or cross-skill privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install nano-banana-2-direct - After installation, invoke the skill by name or use
/nano-banana-2-direct - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Fixed metadata: declared GEMINI_API_KEY requirement and added uv-based dependency install step.
v1.0.0
直接调用 Gemini 3.1 Flash Image Preview API，无需 inference.sh，支持文生图、图生图、多种分辨率
Metadata
Frequently Asked Questions
What is Nano Banana 2 Direct?
Generate/edit images with Gemini 3.1 Flash Image Preview (Nano Banana 2). Direct API call without inference.sh dependency. Use for image create/modify reques... It is an AI Agent Skill for Claude Code / OpenClaw, with 568 downloads so far.
How do I install Nano Banana 2 Direct?
Run "/install nano-banana-2-direct" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Nano Banana 2 Direct free?
Yes, Nano Banana 2 Direct is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Nano Banana 2 Direct support?
Nano Banana 2 Direct is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Nano Banana 2 Direct?
It is built and maintained by xiaofei (@franklu0819-lang); the current version is v1.0.1.
More Skills