$npx skillfedfor your agent

image-gen

Create AI-generated images by describing what you want. Select your preferred model, resolution, and aspect ratio, then optionally add reference images for style guidance. The skill handles the generation and saves your images locally.

image-gen generates AI images from text prompts using Gemini models with customizable resolution and aspect ratios.

AI-generated summary based on this skill's SKILL.md

★ 75  2 MITupdated by marswaveai

Decision gist · record as of 2026-07-16

image-gen generates AI images from text prompts using Gemini models with customizable resolution and aspect ratios. Create AI-generated images by describing what you want. Select your preferred model, resolution, and aspect ratio, then optionally add reference images for style guidance. The skill handles the generation and saves your images locally.

manual: git clone https://github.com/marswaveai/skills → cp -r skills/image-gen ~/.claude/skills/image-gen
image-gen/SKILL.md · version 360e3019

Use it when

  • Yes, image-gen lets you customize both resolution and aspect ratio when creating visual content.
  • image-gen can use style reference images to guide the generation process.

Verify before relying

Read SKILL.md below before installing (3 files). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

marswaveai/skills/image-gen · repository language: HTML

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I generate an image from text with image-gen?

image-gen creates AI-generated images from your text descriptions. Simply describe what you want to visualize, and the skill generates the image based on your prompt. You can customize the resolution and aspect ratio to suit your needs, and optionally provide reference images to guide the style of the generated artwork.

Can image-gen create visual content with customizable resolution?

Yes, image-gen lets you customize both resolution and aspect ratio when creating visual content. This flexibility allows you to generate images tailored to your specific requirements, whether you need cover images, illustrations, concept art, or other visual materials from your text descriptions.

What does image-gen do with style reference images?

image-gen can use style reference images to guide the generation process. By providing reference images, you give the skill visual direction for how your generated artwork should look, helping ensure the output matches your desired aesthetic and style preferences.

Should I choose pro or flash model in image-gen?

image-gen offers both pro and flash models to balance your priorities. Choose the pro model for higher quality images when quality matters most, or select the flash model for faster generation when speed is more important. Your choice depends on whether you prioritize image quality or quick turnaround.

What types of images can image-gen create from descriptions?

image-gen can generate various types of visual content from text prompts, including cover images, illustrations, and concept art. The skill transforms your text descriptions into AI-generated artwork, making it versatile for creative projects, design work, and visualization needs.

SKILL.md

Rendered from the published skill. Quoted content, verbatim.

When to Use

  • User wants to generate an AI image from a text description
  • User says "generate image", "draw", "create picture", "配图"
  • User says "生成图片", "画一张", "AI图"
  • User needs a cover image, illustration, or concept art

When NOT to Use

  • User wants to create audio content (use /podcast, /speech)
  • User wants to create a video (use /explainer)
  • User wants to edit an existing image (not supported)
  • User wants to extract content from a URL (use /content-parser)

Purpose

Generate AI images using the ListenHub CLI. Supports text prompts with optional reference images (local files or URLs), multiple resolutions, and aspect ratios. Images are saved as local files.

Hard Constraints

  • Always check CLI auth following shared/cli-authentication.md
  • Follow shared/cli-patterns.md for command execution and error handling
  • Always read config following

(truncated - see the full file via the links below)

File tree — 3 files
image-gen/SKILL.md
image-gen/references/prompt-guide.md
image-gen/shared

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Generate an AI image from a text description or prompt”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

video-gen
by marswaveai · marswaveai/skills

Create AI-powered videos from text descriptions, images, or reference materials using three distinct model families. Choose HappyHorse for versatile text-to-video and editing, SeeDance for frame-based transitions, or PixVerse for specialized features like lip-sync, motion transfer, and marketing templates.

MITupdated Jul 2026
★ 75repo stars
Nano Banana
by dennisonbertram · dennisonbertram/claude-media-skills

Nano Banana creates images using Google's Gemini image generation models through a straightforward command-line interface. Specify resolution up to 4K, choose from multiple aspect ratios, and optionally enhance prompts for better results—images save locally with automatic notifications.

no license declared → metadata onlyupdated Jan 2026
★ 8repo stars
Image Gen
by InfQuest · InfQuest/vibe-ops-plugin

Image Gen creates pictures from your descriptions using multiple AI models, with options for aspect ratios and batch generation. You can also upload an existing image to edit or transform it based on your instructions.

no license declared → metadata onlyupdated Jan 2026
★ 0repo stars
Baoyu Image Gen
by SpaceZephyr · SpaceZephyr/myskill

Baoyu Image Gen creates images from text prompts using OpenAI, Google, or DashScope providers. Configure default settings, choose quality levels and aspect ratios, and optionally use reference images to guide generation.

no license declared → metadata onlyupdated Mar 2026
★ 331repo stars
Baoyu Image Gen
by oldwinter · oldwinter/skills

Baoyu Image Gen creates images from text prompts using multiple AI providers—OpenAI, Google, DashScope, and Replicate. Choose your preferred provider and model, set aspect ratios and quality levels, and optionally reference existing images to guide generation. Sequential processing is the default; parallel generation is available on request.

no license declared → metadata onlyupdated Jul 2026
★ 4repo stars
happy-image-gen
by iamzhihuix · iamzhihuix/happy-claude-skills

happy-image-gen unifies image generation across eight providers—OpenAI, Google, Replicate, Stability AI, FAL, Ark, Bailian, and SiliconFlow—under a single command-line interface. Create still images from text prompts or transform existing images with reference-driven edits. The skill auto-detects available API keys and respects your configuration defaults, so you can switch providers without rewriting commands.

MITupdated Apr 2026
★ 305repo stars

More skills baoyu-imagine (MIT)

Tags
text-to-imageai-artvisual-generationprompt-basedstyle-referenceaspect-ratio-controlresolution-optionsmulti-modelimage-synthesiscreative-tools