skills.rest
MuseLinn
MuseLinnCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gpt-image-2

Generates and edits images via the GPT Image 2 model using an OpenAI-compatible API.

Updated Jun 12, 2026
Search Tags:#automation#design#image generation#visuals#photo editing#ai art
One-click install
npx skills add https://github.com/MuseLinn/gpt-image-2 --skill gpt-image-2-muselinn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt-image-2
Source: https://github.com/MuseLinn/gpt-image-2/tree/main
Command: npx skills add https://github.com/MuseLinn/gpt-image-2 --skill gpt-image-2-muselinn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the issue of agents failing to utilize modern image generation capabilities, providing a structured, reliable way to create and edit high-quality visuals without the need for manual prompt engineering or ad-hoc API calls.

Core Features & Use Cases

  • Instructional Generation: Create pitch-deck slides, UI mockups, posters, and infographics using intent-first, specific prompts.
  • Surgical Editing: Perform precise local edits using the change ONLY X / preserve Y exactly pattern.
  • Visual Self-Verification: The agent automatically reads and validates generated images against the prompt before presenting them to the user.

Quick Start

Use the gpt-image-2 skill to generate a photorealistic product shot of a ceramic coffee dripper on a wooden counter.

Frequently Asked Questions about gpt-image-2

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

FAQPage Schema
How do I generate UI mockups and pitch-deck slides with AI?▼

AI image generation creates UI mockups and pitch-deck slides by processing intent-first instructional prompts. You provide specific visual descriptions, and the model outputs structured, high-quality graphics without manual design work.

Can I perform precise local edits on photos using an AI model?▼

Precise local photo editing is possible using a change ONLY X / preserve Y exactly pattern. This surgical editing approach modifies specific image regions while keeping the surrounding areas completely intact.

How does visual self-verification work for AI-generated images?▼

Visual self-verification automatically reads and validates generated images against the original prompt before presenting them. This workflow ensures the output strictly adheres to your instructional prompt structure and quality expectations.

Do I need external dependencies to use an OpenAI-compatible API for image generation?▼

No external dependencies are required to run image generation and editing tasks. The Skill operates through a zero-dependency CLI, providing a robust interface to interact directly with the OpenAI-compatible API.

Why do agents fail at modern image generation and how to fix it?▼

Agents fail at modern image generation due to ad-hoc API calls and lack of prompt engineering. This is fixed by providing a structured, reliable interface that enforces strict instructional prompt structures for consistent visual outputs.

Related Skills

Explore More Design & Creative Skills→
joelklabojoelklabo

sketch-ai-provider-debug

Debug OpenAI and Gemini image generation failures for Sketch Magic /api/convert requests.

Community
Intermediate
FacundoSu1986FacundoSu1986

ckm:design

Coordinate brand identity across design systems, CIP deliverables, and presentation assets.

Community
Advanced
kingkillerykingkillery

doc

Analyze and improve DOCX document layout with visual review tools.

Community
Intermediate
diegocamara89diegocamara89
3

imagegen

Generate and edit images via the OpenAI Image API using a bundled CLI.

Community
Advanced