← Back to Skills Marketplace
87
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install nanobanana-openrouter
Description
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image) via OpenRouter. Use for image create/modify requests incl. edits. Supports text-to-image + ima...
Usage Guidance
Before installing, be aware of three issues: (1) the skill actually requires an OpenRouter API key (OPENROUTER_KEY) and the 'uv' runner but the metadata does not declare them — ask the author to update the manifest so you know what credentials will be used; (2) the scripts will upload any file you point at with --input-image (it encodes the file as a data URL and sends it to openrouter.ai) — do not pass paths to sensitive local files; and (3) filenames are not sanitized against directory traversal (a crafted --filename or --output-dir could cause writes outside the skill folder). If you still want to use it, run it in a sandboxed environment, only provide a dedicated API key with limited quota/permissions, and request the author add explicit metadata and filename/path sanitization (reject '..' or absolute paths, enforce basename-only writes).
Capability Analysis
Type: OpenClaw Skill
Name: nanobanana-openrouter
Version: 1.1.1
The skill bundle provides a legitimate interface for generating and editing images via the OpenRouter API (Google Gemini 3 Pro Image). The Python scripts (generate_image.py and generate_and_return.py) use standard libraries like requests and Pillow to handle API communication and image processing, and they employ safe subprocess execution patterns. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description match the included code (calls OpenRouter to generate/edit images). However the registry metadata declares no required environment variables or binaries while the SKILL.md and scripts require an OpenRouter API key (OPENROUTER_KEY) and the 'uv' runner. That mismatch is incoherent: a user or integrator would reasonably expect OPENROUTER_KEY to be declared as a required credential and 'uv' as a required binary.
Instruction Scope
SKILL.md instructs the agent to run the provided scripts for generation and edits, which is consistent. But the scripts convert any provided input image to a base64 data URL and POST it to openrouter.ai — meaning arbitrary local files supplied as --input-image will be uploaded to an external service. SKILL.md does not explicitly warn about uploading local files, and the code does not restrict which paths may be supplied.
Install Mechanism
This is instruction-plus-scripts only: there is no install spec or remote download. That minimizes supply-chain risk; dependencies are declared in script comments (requests, pillow) but nothing is fetched at install time by the skill bundle.
Credentials
The code requires an OpenRouter API key (OPENROUTER_KEY) or --api-key at runtime, but the skill metadata declares no required env vars and primary credential is 'none'. This is a clear mismatch. Requesting the single API key is proportional for this purpose, but it should be declared explicitly. No other credentials are requested.
Persistence & Privilege
The skill is not always-enabled and does not request special platform privileges. It writes output images to a local output_images directory under the skill by default (or to a user-specified output-dir).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install nanobanana-openrouter - After installation, invoke the skill by name or use
/nanobanana-openrouter - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.1
- Updated usage instructions to use `/path/to/this/skill/` instead of an absolute `.openclaw` or `.codex` path.
- Changed the default output directory from `~/.openclaw/skills/nano-banana-pro-openrouter/output_images/` to `./output_images/` relative to the skill's root.
- All example commands reflect the new path conventions.
- No functional or code changes detected; documentation clarification only.
v1.1.0
- Adds detailed usage instructions for Nano Banana Pro image generation and editing via OpenRouter (Gemini 3 Pro Image).
- Supports both text-to-image and image-to-image (edits) with multiple resolution options: 1K, 2K, and 4K.
- Explains filename generation with timestamp and descriptive text, plus fallback to random identifiers.
- Outlines API key configuration and error handling for common issues.
- Provides prompt handling advice and ready-to-use templates for both generation and editing scenarios.
- Documents default workflow for efficient image creation and iteration.
Metadata
Frequently Asked Questions
What is nanobanana-openrouter?
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image) via OpenRouter. Use for image create/modify requests incl. edits. Supports text-to-image + ima... It is an AI Agent Skill for Claude Code / OpenClaw, with 87 downloads so far.
How do I install nanobanana-openrouter?
Run "/install nanobanana-openrouter" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is nanobanana-openrouter free?
Yes, nanobanana-openrouter is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does nanobanana-openrouter support?
nanobanana-openrouter is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created nanobanana-openrouter?
It is built and maintained by chang (@liberalchang); the current version is v1.1.1.
More Skills