# Draw Image

> Generate an image from a text prompt using the default OpenAI-like LLM config (gpt-image-1-mini or compatible image generation API). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned.

- **Type:** Skill
- **Install:** `agentstack add skill-ai-sns-ai-sns-draw-image`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ai-sns](https://agentstack.voostack.com/s/ai-sns)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ai-sns](https://github.com/ai-sns)
- **Source:** https://github.com/ai-sns/ai-sns/tree/master/aisns_backend/skills/draw-image
- **Website:** https://www.ai-sns.org

## Install

```sh
agentstack add skill-ai-sns-ai-sns-draw-image
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Draw Image

Generate images via the OpenAI-compatible `images/generations` endpoint using the default LLM configuration.

## Parameters

This skill accepts a JSON object as input params.

- `prompt` (string, **required**)
  - The text description of the image to generate.

- `size` (string, optional)
  - Image dimensions. Default: `1024x1024`
  - Common values: `1024x1024`, `1792x1024`, `1024x1792`

- `model` (string, optional)
  - The image generation model name. Default: `gpt-image-1-mini`

- `quality` (string, optional)
  - Image quality. Values: `low`, `medium`, `high`. Default: `low`

- `n` (integer, optional)
  - Number of images to generate. Default: `1`

## How to use

1. Call `read_skill` with `skill_key: "draw_image"` to read this document.
2. Then call `run_doc_skill` with `skill_key: "draw_image"` and `params`.

Example:

```json
{
  "skill_key": "draw_image",
  "prompt": "A futuristic cityscape at sunset with flying cars",
   "size": "1024x1024"

}
```

## Output

The runner prints a JSON object to stdout with:

- `ok` (bool): Whether the generation and upload succeeded.
- `download_page` (string): The public gofile.io download page URL of the generated image. **Only this URL is returned** as the result. Open this URL in a browser to download the generated image.
- `note` (string): A short hint explaining that `download_page` is used to download the generated image.
- `error` (string): Error message on failure.

Example success output:

```json
{
  "ok": true,
  "download_page": "https://gofile.io/d/WcWZKt",
  "note": "Use this URL to download the generated image."
}
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ai-sns](https://github.com/ai-sns)
- **Source:** [ai-sns/ai-sns](https://github.com/ai-sns/ai-sns)
- **License:** MIT
- **Homepage:** https://www.ai-sns.org

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ai-sns-ai-sns-draw-image
- Seller: https://agentstack.voostack.com/s/ai-sns
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.