Skip to content
Agentmart
Submit a tool

generating-images

Generates images using AI models (Gemini).

Skill by Yusufkotavom

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/yusufkotavom-generating-images

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generates images using AI models (Gemini). AI图像生成、文生图、生成图片。

Use cases: backend, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/generating-images

What's inside

Skill name
generating-images
Description
Generates images using AI models (Gemini). AI图像生成、文生图、生成图片。
License
MIT
Instructions
128 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Image Generation

Generates images using Gemini AI model (default: gemini-3.1-flash-image-preview, compatible: gemini-3-pro-image-preview).

## Parameters

### Required

- `prompt`: Creative description of the image

### Optional

- `imageUrls`: Reference image URLs for editing
- `imageSize`: Output resolution - "1K", "2K", "4K"
- `aspectRatio`: "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"

## Workflow

1. Call `generateImage` with prompt and optional parameters
2. Image generation is synchronous - returns URL immediately

## Multiple Images Strategy

- Call `generateImage` sequentially
- Display each image immediately with progress (e.g., "已生成 1/3")
- Use markdown `![desc](url)` format

## Prompt Writing Guide

### Core Principle

**Describe the scene, don't just list keywords.** Narrative descriptions always outperform keyword lists.

### Scene Strategies

#### 1. Photorealistic Scenes

Include photography terms: lens type, lighting, atmosphere

- Example: `A photorealistic close-up portrait of an elderly Japanese ceramicist with deep, sun-etched wrinkles and a warm, knowing smile. He is carefully inspecting a freshly glazed tea bowl.`

#### 2. Stylized Illustrations

Specify style, features, and background requirements

- Example: `A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette.`

#### 3. Text-Accurate Images

Specify font style, design approach, and color scheme

- Example: `Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white.`

#### 4. Product Photography

Describe studio setup, lighting configuration, camera angle in detail

- Example: `A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface.`

#### 5. Minimalist Design

Subject positioning strategy, reserve negative space

- Example: `A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas.`

#### 6. Sequential Art (Comics/Storyboards)

Emphasize character consistency and scene description

- Example: `Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humorous scene.`

#### 7. Search-Grounded Graphics

Combine with search tools to get current events/weather/trends for timely content

- Example: `Make a simple but stylish graphic of last night's Arsenal game in the Champion's League`

## Language Guidelines

Text in generated images MUST match user's language.

## Examples

### Photorealistic Scene

```
generateImage:
  prompt: "A photorealistic close-up portrait of an elderly Japanese ceramicist with deep, sun-etched wrinkles and a warm, knowing smile. He is carefully inspecting a freshly glazed tea bowl."
  aspectRatio: "3:4"
  imageSize: "2K"
```

### Stylized Illustration

```
generateImage:
  prompt: "A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette."
  aspectRatio: "1:1"
  imageSize: "1K"
```

### Product Photography

```
generateImage:
  prompt: "A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface."
  aspectRatio: "1:1"
  imageSize: "2K"
```

### Minimalist Design

```
generateImage:
  prompt: "A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas."
  aspectRatio: "16:9"
  imageSize: "2K"
```

From Yusufkotavom/AiToEarn, MIT.

More from Yusufkotavom/AiToEarn

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 17, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Yusufkotavom

Cite this page

generating-images skill. Agent Mart. https://agentmart.dev/skills/yusufkotavom-generating-images (last updated 2026-10-24)