gpt-image-2

Community

Three-mode image generation/editing for agents

AuthorConardLi
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides end-to-end image generation and editing capabilities for AI agents across three runtime modes (Garden local, Host-Native, and Advisor), enabling deterministic prompts, rendering, and prompt archival outputs loaded into context during activation.

Core Features & Use Cases

  • Mode-aware workflow: gracefully degrades from full generation to prompt advisory when image tools are unavailable.
  • Structured prompt templates: supports 18 categories and 80+ templates to cover posters, UI mockups, product visuals, infographics, academic figures, architectural diagrams, and more.
  • Deterministic execution: includes scripts/check-mode.js, generate.js, and edit.js to ensure reproducible tasks and archivable outputs.
  • OpenAI-compatible by default: uses OpenAI-compatible interfaces and avoids vendor lock-in, with environment-driven configuration and archival of prompts and outputs.

Quick Start

Provide a prompt and run the mode detector to choose the runtime path, then generate or edit an image with the corresponding script.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: gpt-image-2
Download link: https://github.com/ConardLi/garden-skills/archive/main.zip#gpt-image-2

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.