← Back to Skills Marketplace
8379
Downloads
3
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install gemini-image-simple
Description
Generate and edit images with Gemini API using pure Python stdlib. Zero dependencies - works on locked-down environments where pip/uv aren't available.
Usage Guidance
Install only if you are comfortable sending prompts, selected input images, and related request data to Google's Gemini API under your API key. Use a key intended for this purpose, monitor quota or billing, and avoid submitting confidential, regulated, or private images unless that external processing is acceptable.
Capability Analysis
Type: OpenClaw Skill
Name: gemini-image-simple
Version: 1.1.0
The skill is classified as benign. The `SKILL.md` provides clear instructions for image generation and editing using the Gemini API, requiring only the `GEMINI_API_KEY` environment variable. The `scripts/generate.py` script implements this functionality using standard Python libraries (`urllib.request`, `json`, `base64`), connecting to the legitimate Google Gemini API endpoint (`https://generativelanguage.googleapis.com/v1beta/models/nano-banana-pro-preview:generateContent`). It reads user-specified input image files and writes generated output image files, which is directly aligned with its stated purpose. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, prompt injection attempts against the agent, or obfuscation.
Capability Assessment
Purpose & Capability
The documented purpose is image generation/editing, and the script implements only that workflow using a prompt, optional input image, Gemini API request, and caller-chosen output file.
Instruction Scope
The runtime instructions are user-directed command examples with no hidden agent-control behavior, prompt-injection content, autonomous execution, or unrelated tasks.
Install Mechanism
There is no dependency installer, package bootstrap, or shell setup beyond requiring Python and a GEMINI_API_KEY environment variable.
Credentials
Network use and the GEMINI_API_KEY are proportionate for a Gemini integration, but users should understand that prompts and selected input images are transmitted to Google's API.
Persistence & Privilege
The script writes generated image bytes to a user-specified output path and may create parent directories; this is expected, though users should choose paths carefully to avoid overwriting files.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install gemini-image-simple - After installation, invoke the skill by name or use
/gemini-image-simple - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
- Switched image generation model to "Nano Banana Pro" (`nano-banana-pro-preview`), delivering highest quality image generation (Gemini 3 Pro Image).
- Updated documentation to reflect the new model and its aliases, including information about alternative models.
- Enhanced "How It Works" and "Model" sections in SKILL.md for clarity and transparency.
- All functionality remains dependency-free and continues to work on any Python 3.10+ installation.
v1.0.0
Initial release - zero-dependency Gemini image generation
Metadata
Frequently Asked Questions
What is Gemini Image Simple?
Generate and edit images with Gemini API using pure Python stdlib. Zero dependencies - works on locked-down environments where pip/uv aren't available. It is an AI Agent Skill for Claude Code / OpenClaw, with 8379 downloads so far.
How do I install Gemini Image Simple?
Run "/install gemini-image-simple" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Gemini Image Simple free?
Yes, Gemini Image Simple is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Gemini Image Simple support?
Gemini Image Simple is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Gemini Image Simple?
It is built and maintained by Cluka-399 (@cluka-399); the current version is v1.1.0.
More Skills