skills.rest
ConardLi
ConardLiCOMMUNITY
Explore all skills by this author →
Website𝕏@GardenConardLiGitHub

gpt-image-2

Generate and edit images across Garden local, Host-Native, and Advisor modes.

10.2k|1.3k|Updated Apr 21, 2026
Search Tags:#image-generation#advisor#prompt-engineering#garden#gpt-image-2#host-native
One-click install
npx skills add https://github.com/ConardLi/garden-skills --skill gpt-image-2
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt-image-2
Source: https://github.com/ConardLi/garden-skills/tree/main/skills/gpt-image-2
Command: npx skills add https://github.com/ConardLi/garden-skills --skill gpt-image-2

SYSTEM DOCUMENTATION & REQUIREMENTS

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

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.

Frequently Asked Questions about gpt-image-2

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

FAQPage Schema
How do I automate image generation within an AI agent workflow?▼

Image generation within an agent workflow uses structured prompt templates and deterministic scripts to render visuals. The system detects available runtime modes and executes the matching generation or editing script to produce reproducible image outputs.

Can I use OpenAI-compatible interfaces for agent image generation without vendor lock-in?▼

Yes, OpenAI-compatible interfaces support agent image generation without vendor lock-in by using environment-driven configuration. This approach avoids hardcoding specific vendor APIs while maintaining deterministic prompt execution and output archival.

How do I edit existing images using an AI agent?▼

Editing existing images with an AI agent requires running the dedicated edit.js script after the mode detector identifies the active runtime. The agent applies structured prompt templates to modify the image and archives the resulting output deterministically.

What happens to image generation tasks when rendering tools are unavailable in the environment?▼

When rendering tools are unavailable, the image generation workflow gracefully degrades from full rendering to a prompt advisory mode. This ensures the agent can still generate and archive structured prompts for later use instead of failing the task.

Are there structured prompt templates for generating specific visual formats like UI mockups or infographics?▼

Structured prompt templates cover 18 categories and 80+ variations for generating visual formats. These templates support creating UI mockups, infographics, product visuals, academic figures, and architectural diagrams by providing deterministic prompt structures.

How do I ensure reproducible image generation outputs across different agent runs?▼

Reproducible image generation outputs are ensured by using deterministic execution scripts and a frontmatter-driven template system. The environment-variable resolution and output archiving mechanisms guarantee that identical prompts yield consistent results across runs.

Related Skills

Explore More Design & Creative Skills→
Free-The-AiFree-The-Ai
833

freetheai-api

Access FreeTheAi's OpenAI-compatible API for text, image, and audio tasks.

Official
Advanced
hybridindiehybridindie
2

Generation History

Retrieve recent ComfyUI image generation jobs with statuses and output files.

Community
Basic
RightNow-AIRightNow-AI
18.1k

prompt-engineer

Design prompts for chain-of-thought, few-shot learning, and structured output.

Official
Intermediate
bibo1243bibo1243

image-gen

Generate images from prompts and upload them to Catbox for sharing via LINE or Telegram.

Community
Intermediate