skills.rest
Yoodaddy0311
Yoodaddy0311COMMUNITY
Explore all skills by this author →
GitHub

image-generation

Generates English image prompts via a 7-mode system and executes them through the Gemini API.

3|2|Updated Feb 13, 2026
Search Tags:#prompt engineering#image generation#logo design#gemini api#illustration#thumbnail#multi-turn refinement
One-click install
npx skills add https://github.com/Yoodaddy0311/artibot --skill image-generation-yoodaddy0311
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-generation
Source: https://github.com/Yoodaddy0311/artibot/tree/main/plugins/artibot/skills/image-generation
Command: npx skills add https://github.com/Yoodaddy0311/artibot --skill image-generation-yoodaddy0311

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning a vague natural-language request into a high-quality image generation prompt is hard, and iterating on previous results without losing context is even harder. This Skill structures prompt engineering for image creation and optionally executes the prompt against an external image API. ## Core Features & Use Cases - 7-Mode Prompt Engineering: Automatically selects among portrait, landscape, object, illustration, thumbnail, logo, and conceptual modes, each with its own persona, workflow, and output template. - Three Operation Modes: Detects whether the request is a new generation (MODE_NEW), an edit of an existing image file (MODE_EDIT), or a refinement of a previous result in the conversation (MODE_REFINE), then adjusts the prompt accordingly. - Parameter Auto-Mapping: Extracts aspect ratio (1:1, 3:4, 16:9, 4:1) and quality hints from keywords like "thumbnail", "portrait", or "draft". - Gemini API Execution: When GEMINI_API_KEY is set, calls the Gemini REST API to generate the image; otherwise outputs the prompt for use in Midjourney, DALL-E, or AI Studio. - Use Case: Ask for a YouTube thumbnail in Korean, receive a 16:9 English prompt, get the image generated via Gemini, then say "make it brighter" to trigger a refinement loop. ## Quick Start Ask the assistant to generate an image, for example: "Create a YouTube thumbnail for my coding tutorial video."

Frequently Asked Questions about image-generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an image from a text description?▼

Describe the image you want in natural language, including hints like orientation or quality. The skill selects one of seven modes (portrait, landscape, object, illustration, thumbnail, logo, conceptual), builds a detailed English prompt, and generates the image via the Gemini API if a key is configured.

How do I edit or refine an image I already generated?▼

Reference the previous result with phrases like "make it brighter" or "change the colors" and the skill enters MODE_REFINE, producing a delta prompt based on the last generation. Providing an existing image file path triggers MODE_EDIT instead.

Does image generation work without a Gemini API key?▼

Yes, but only the prompt is produced. Without GEMINI_API_KEY set, the skill outputs the full English prompt plus recommended aspect ratio and instructions to run it in Google AI Studio, Midjourney, or DALL-E.

What aspect ratios does the image generation skill support?▼

It maps keywords to four ratios: 3:4 for portrait/poster content, 16:9 for thumbnails and landscape, 1:1 for profile icons and squares, and 4:1 for banners. If no hint is detected, it defaults to 1:1 at high quality.

When should I not use this image generation skill?▼

Avoid it for text-only content creation, code generation, or any task that does not involve creating, editing, or refining visual image assets. It is scoped strictly to image prompt engineering and generation workflows.

Related Skills

Explore More Design & Creative Skills→
AgriciDanielAgriciDaniel
7.9k

ads-generate

Generate ad creative images from campaign briefs and brand profiles.

Community
Advanced
larsboeslarsboes

Media

Generate visual assets from text prompts and design briefs.

Community
Intermediate
PatrickjoshanedezPatrickjoshanedez

anti-slop

Detect and remove generic AI-generated patterns from text files.

Official
Intermediate
pikakitpikakit

ai-artist

Generate deterministic, templated prompts for text and image generation models.

Community
Advanced