Agent skill

generate_image

View SKILL.md on GitHub Repository
Stars 0
Forks 1

Install this agent skill to your Project

npx add-skill https://github.com/The-Focus-AI/weekend-coding-agent/tree/main/skills/generate_image

SKILL.md

Generate Image

Generate or edit images using Gemini models via @the-focus-ai/nano-banana.

Requirements

  • npx must be installed.
  • GEMINI_API_KEY environment variable must be set.

Usage

bash
npx @the-focus-ai/nano-banana "prompt" --output "output_path" [options]

Prompting Best Practices (Imagen 3)

For best results, construct your prompt using this structure: Subject → Context/Background → Style/Medium → Technical Specs

  • Subject: Clearly define the main subject.
  • Context: Describe the environment and lighting.
  • Style: Specify the artistic style (e.g., "oil painting", "cinematic photo", "3d render").
  • Technical Specs: For photorealism, specify camera parameters (e.g., "85mm lens", "f/1.8 aperture", "4k", "HDR").

Tips:

  • Natural Language: Use natural sentences rather than just keywords. Paint with adjectives.
  • Semantic Negative Prompting: Instead of saying what not to include (flakey in this model), describe the absence positively (e.g., "empty sky", "deserted street").
  • Text: If you want text, keep it short and enclose it in quotes.

Parameters

  • prompt (string, required): The description of the image to generate.
  • output_path (string, required): File path to save the generated image (e.g., "images/sunset.png").
  • input_image (string, optional): Path to an existing image to edit.
  • use_flash (boolean, optional): Set to true to use the faster Gemini 2.0 Flash model.

Examples

Generate a new image

bash
npx @the-focus-ai/nano-banana "A futuristic city skyline at sunset, cyberpunk style, neon lights, 8k resolution, cinematic lighting" --output "images/cyberpunk_city.png"

Edit an existing image

bash
npx @the-focus-ai/nano-banana "Make the sky purple and add a spaceship" --file "images/original.png" --output "images/edited.png"

Fast generation

bash
npx @the-focus-ai/nano-banana "A cute cartoon cat" --flash --output "images/cat.png"

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

The-Focus-AI/weekend-coding-agent

generate_video

0 1
Explore
The-Focus-AI/weekend-coding-agent

big_text

Create ASCII art banners using figlet. Use this when the user asks for big text, banners, or ASCII art.

0 1
Explore
The-Focus-AI/nano-banana-cli

Nano Banana Video Generation

Generate videos using Google Veo models via the nano-banana CLI. Use this skill when the user asks to create, generate, animate, or produce videos with AI. Supports text-to-video, image-to-video animation, dialogue with lip-sync, and scene extensions. Trigger on requests like "create a video", "animate this image", "make a video clip", "generate footage", "produce a short film", "add motion to this".

14 2
Explore
The-Focus-AI/nano-banana-cli

Nano Banana Image Generation

Generate and edit images using Google Gemini image models. Use this skill when the user asks to create, generate, make, or edit images with AI. Supports text-to-image, image editing, style transfer, and multi-image composition. Trigger on requests like "create an image", "generate a picture", "make me a logo", "edit this photo", "add X to this image".

14 2
Explore
The-Focus-AI/chrome-driver

browser-automation

Automate Chrome browser via DevTools Protocol. Use when user asks to scrape websites, take screenshots, generate PDFs, interact with web pages, extract content, fill forms, or automate browser tasks.

0 0
Explore
mattpocock/skills

edit-article

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

111,310 9,758
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results