ai-create-image

Generate PNG images from text prompts using the OpenAI Images API.

Updated May 17, 2026
One-click install
npx skills add https://github.com/bennoloeffler/claude-code-personal-agent-plugins-skills --skill ai-create-image
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-create-image
Source: https://github.com/bennoloeffler/claude-code-personal-agent-plugins-skills/tree/main/skills/ai-create-image
Command: npx skills add https://github.com/bennoloeffler/claude-code-personal-agent-plugins-skills --skill ai-create-image

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

It solves the problem of turning an idea or text prompt into a usable visual (image/poster/illustration) without manual design or diagramming work.

Core Features & Use Cases

  • OpenAI gpt-image-1 image generation: Creates PNGs from text prompts for visuals like posters, editorial illustrations, and hero images.
  • Deterministic output artifacts: Writes the generated image to output/YYYY-MM-DD/<name>.png and saves a companion prompt file (<name>.prompt.txt) for reproducibility.
  • Install-time gate + key validation: Uses preflight scripts to verify Node.js >= 18 and validates OPENAI_API_KEY via a live call before the skill is considered ready.

Quick Start

Tell Claude Code: generate a poster for "Lagerfeuer 2026 - KI im Mittelstand" in a warm orange and dark teal style.

Frequently Asked Questions about ai-create-image

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

FAQPage Schema
How do I generate PNG images from text prompts for landing-page visuals?

Image generation from text prompts produces PNG assets for posters, editorial illustrations, and hero images. The Skill uses the OpenAI gpt-image-1 API to translate descriptive text prompts into visual graphics suitable for landing pages, slides, and blog artwork.

Do I need an OpenAI API key to generate illustrations with gpt-image-1?

Yes, generating illustrations with gpt-image-1 requires a valid OPENAI_API_KEY. The workflow executes a preflight install gate that verifies Node.js >= 18 and validates the key via a live OpenAI API call before proceeding.

How do I create a poster using OpenAI image generation in a creative workflow?

To create a poster, provide a descriptive text prompt to the OpenAI Images API workflow. The system outputs a PNG file and a companion prompt text file, ensuring deterministic output artifacts for your creative workflow reproducibility.

Does the gpt-image-1 image generation workflow support Node.js environments?

Yes, the image generation workflow supports Node.js environments. It requires Node.js version 18 or higher, running preflight scripts to verify the environment before executing OpenAI Images API calls to generate PNG assets.

How are generated images and prompts saved for reproducibility in editorial workflows?

Generated images and prompts are saved as deterministic output artifacts. The workflow writes the PNG file to an output/YYYY-MM-DD directory and saves a companion prompt text file, ensuring reproducibility for editorial and creative workflows.

What are the limitations of using OpenAI gpt-image-1 for blog artwork creation?

Limitations include the strict dependency on a valid OPENAI_API_KEY and Node.js >= 18 environment. Additionally, the workflow outputs exclusively PNG files, meaning users requiring other formats must handle external conversion for their blog artwork.