# Create Gemini Image Assets

Teams need quick visual assets without leaving their coding workflow. This skill uses a local Python script to generate images with Gemini and save them into project folders.

## Install

```bash
npx skillstore add lxfater/nano-image-generator
```

## Metadata

- Status: approved
- Slug: lxfater-nano-image-generator
- Skillstore revision: r1
- Version status: missing
- Tree hash: 65f20336184c2884b28e073086a56030825dfffc53b445c44b0b19b0884bb25b
- Author: lxfater
- GitHub username: lxfater
- License: MIT
- Repository: https://github.com/lxfater/nano-image-generator-skill/tree/main/
- Ref: 62e2a730c5cd74eab4c7164309d810de660fcea3
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: confirmation\_required
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: network, filesystem, env\_access, external\_commands
- Quality score: 38
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/lxfater-nano-image-generator
- Manifest: https://skillstore.pages.dev/api/skills/lxfater-nano-image-generator/manifest

## Capabilities

- Generates images from text prompts through Gemini 3 Pro Preview.
- Supports square, portrait, landscape, mobile, and cinematic aspect ratios.
- Accepts up to 14 reference images for style transfer or character consistency.
- Writes generated images to a caller-selected local output path.
- Detects returned image format and adjusts the saved file extension.
- Offers 1K, 2K, and 4K output size options.

## Use Cases

- Generate Product Graphics: Create app icons, UI assets, and feature illustrations directly from project prompts.
- Produce Campaign Images: Create banners, social images, and launch visuals with selected aspect ratios and sizes.
- Maintain Visual Consistency: Use reference images to keep a consistent style or character across a sequence of assets.

## Prompt Templates

### Basic Image

```
Generate an image of a friendly robot mascot waving, with a clean modern style, and save it to the generated folder.
```

### Sized Banner

```
Create a 16:9 website hero banner for a productivity app with abstract geometric shapes and a calm professional color palette.
```

### Reference Style

```
Use the reference image as the visual style and generate a new mountain scene with matching colors, lighting, and texture.
```

### Consistent Series

```
Generate a three-image knowledge card series with a consistent layout, matching typography space, and a clear visual theme.
```

## Limitations

- Requires a Gemini API key configured inside the Python script.
- Sends prompts and reference images to the Google Gemini API.
- Generated text and exact brand marks may be unreliable.
- Requires local Python, network access, and write access to the output folder.

## Best Practices

- Use specific prompts with subject, style, colors, composition, and intended use.
- Store generated assets in project folders that match their purpose.
- Review reference images before sending them to the external API.

## Anti Patterns

- Do not hardcode real API keys in files committed to source control.
- Do not send private reference images unless external processing is acceptable.
- Do not rely on generated images for exact text, trademarks, or final brand approval.

## Security Audit

- Audited at: 2026-07-05T21:44:24.805\+00:00
- Summary: The skill provides a legitimate Gemini-backed image generation workflow, but it has meaningful security concerns. The main confirmed issues are hardcoded API key setup, external transfer of prompts and reference images, local Python command execution, and unrestricted output-path writes. Documentation-only URLs, Markdown formatting, magic-byte checks, and response image base64 decoding were adjudicated as false positives.

## Stats

- Views: 273
- Downloads: 64
- Favorites: 2
- Popularity score: 0