optimize-images

Full Plugin (recommended - includes all skills):

```bash

/plugin marketplace add b-open-io/claude-plugins

/plugin install gemskills@b-open-io

```

Individual Skills (for other agentic frameworks):

```bash

bunx skills add b-open-io/gemskills --skill generate-image

bunx skills add b-open-io/gemskills --skill browsing-styles

bunx skills add b-open-io/gemskills --skill pixel-avatar

bunx skills add b-open-io/gemskills --skill team-group-photo

bunx skills add b-open-io/gemskills --skill generate-icon

bunx skills add b-open-io/gemskills --skill edit-image

bunx skills add b-open-io/gemskills --skill upscale-image

bunx skills add b-open-io/gemskills --skill segment-image

bunx skills add b-open-io/gemskills --skill optimize-images

bunx skills add b-open-io/gemskills --skill generate-svg

bunx skills add b-open-io/gemskills --skill section-dividers

bunx skills add b-open-io/gemskills --skill deck-creator

bunx skills add b-open-io/gemskills --skill ask-gemini

```

Requirements:

• GEMINI_API_KEY - Google AI Studio API key ([get one here](https://aistudio.google.com/apikey))
• REPLICATE_API_TOKEN - Required for generate-icon background removal ([get one here](https://replicate.com/account/api-tokens))

Image Generation

| Skill | Description |

|-------|-------------|

| generate-image | AI image generation with 100+ art styles, multi-reference support (up to 14 images), img2img transformations |

| browsing-styles | Browse and preview all available art styles - impressionism, ukiyo-e, cyberpunk, pixel art, and 96 more |

| pixel-avatar | Create pixel art avatars from reference photos maintaining likeness |

| team-group-photo | Composite pixel art team portraits with multiple people |

| generate-icon | Generate platform-specific icons (favicon, iOS, Android, PWA, desktop) with automatic sizing |

Image Editing & Processing

| Skill | Description |

|-------|-------------|

| edit-image | Inpainting and outpainting with masks |

| upscale-image | 2x/4x upscaling via Vertex AI (requires Google Cloud credentials) |

| segment-image | Identify and extract objects from images |

| optimize-images | Batch compress PNGs/JPEGs for web using sharp |

Design & Content

| Skill | Description |

|-------|-------------|

| generate-svg | Create vector graphics, logos, and icons |

| section-dividers | Transparent decorative dividers for web page sections |

| deck-creator | Generate complete presentation decks with consistent visual style |

Text & Vision

| Skill | Description |

|-------|-------------|

| ask-gemini | Query Gemini with text and up to 10 images - ideal for design critique and spatial analysis |

```bash

# Generate an image with art style

"Generate a mountain landscape in watercolor style"

# Create pixel avatar from photo

"Create a pixel art avatar from my headshot"

# Analyze a design

"Compare these two landing pages - what works better?"

# Optimize images for production

"Optimize the images in public/images for web"

# Create presentation slides

"Create a pitch deck for my startup"

# Generate app icons for all platforms

"Generate a favicon for my website with a lightning bolt"

"Create iOS app icons for my meditation app"

```

• Image generation: Gemini 3 Pro produces high-quality images with excellent prompt following
• 100+ art styles: Built-in style library with real museum references
• Multi-image input: Use up to 14 reference images for character consistency and scene composition
• Spatial reasoning: Superior visual understanding for design feedback

MIT