skills.rest
jykim
jykimCOMMUNITY
Explore all skills by this author →
GitHub

image-generation-skill

Generate 1024x1024 images via DALL-E 3 for documents and slide decks.

49|9|Updated Nov 26, 2025
Search Tags:#visuals#slides#prompts#image-generation#DALL-E
One-click install
npx skills add https://github.com/jykim/claude-obsidian-skills --skill image-generation-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-generation-skill
Source: https://github.com/jykim/claude-obsidian-skills/tree/main/image-generation-skill
Command: npx skills add https://github.com/jykim/claude-obsidian-skills --skill image-generation-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai.

What problem does it solve?

Creating visuals for documents and presentations can be time-consuming. This skill automatically generates consistent images in your chosen style to enhance clarity and engagement.

Core Features & Use Cases

  • Automatic style selection: Choose from multiple visual styles to match the document tone.
  • Consistent visuals: Maintain a uniform look across all generated images.
  • Cost awareness: Provides upfront cost estimates per image.
  • Use Case: Generate a set of 6 slide illustrations in a cohesive style for a 10-slide deck.

Quick Start

Request: "Generate images for my presentation in Vibrant Modern Cartoon style."

Frequently Asked Questions about image-generation-skill

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

FAQPage Schema
How do I add images to my presentation slides automatically?▼

This Skill analyzes your slide content, identifies sections without visuals, and generates 1024x1024 images via DALL-E 3 in your chosen style, then inserts them with updated captions. You need an OpenAI API key and select from preset visual styles like Vibrant Modern Cartoon or others available in the Skill.

Can I generate consistent images across an entire document or deck?▼

Yes. The Skill maintains uniform visual styling across all generated images by applying your selected style consistently. It works on both documents and presentation decks, ensuring cohesive appearance throughout.

What does it cost to generate images with DALL-E 3?▼

The Skill provides upfront cost estimates per image before generation, so you know the expense in advance. Actual costs depend on DALL-E 3 pricing and your OpenAI API plan.

Do I need to manually approve each generated image before it's added?▼

The Skill supports both automatic insertion and interactive approval workflows. You can review and approve images before they're placed, or enable automatic placement depending on your preference.

What visual styles are available for generated images?▼

The Skill includes a preset list of visual styles to choose from. Select the style that matches your document tone—such as Vibrant Modern Cartoon or others—and the Skill applies it consistently across all generated images.

What happens to speaker notes and captions when images are inserted?▼

The Skill automatically updates captions and speaker notes when placing generated images, maintaining document context and coherence alongside the new visuals.

Related Skills

Explore More Design & Creative Skills→
ckt520728ckt520728

lecture-notes

Convert lecture audio and presentation slides into structured notes with NotebookLM MCP and DALL-E.

Community
Advanced
zephyrwang6zephyrwang6
58

baoyu-slide-deck

Generate slide deck outlines, prompts, and images from content.

Community
Advanced
liumeixinliumeixin
4

wenyan-xhs-image-orientation

Detect landscape or portrait orientation of images in Wenyan editor documents.

Community
Advanced
auldsyababuaauldsyababua
6

social-media-generator

Generate platform-optimized social media posts for Twitter, Instagram, LinkedIn, and Facebook.

Community
Intermediate