CommunityImagegithub.com

GPT Image 2 - Image Generation & Editing Skill

A skill for image generation and editing tailored for GPT Image 2. It operates in three modes: (A) Garden local mode for direct image output via an OpenAI-compatible interface, (B) Host-Native mode as a prompt engineering guide, and (C) Advisor mode as a high-quality prompt consultant. Covers 18 categories with 80+ structured templates for posters, UI, products, infographics, academic figures, technical architecture diagrams, comics, avatars, process boards, storyboards, IP merchandise, and editing workflows.

What is GPT Image 2 - Image Generation & Editing Skill?

This skill, conardli/gpt-image-2, is specifically designed for image generation and editing using GPT Image 2. It provides a flexible three-mode architecture to adapt to various environments. In Garden local mode, it leverages an OpenAI-compatible API to directly generate and save images locally. In Host-Native mode, the skill acts as a prompt engineering guide, constructing optimized prompts for the host agent's native image tools. Finally, in Advisor mode, when no image tools are available, it degenerates into a high-quality prompt consultant, offering expert advice. The skill includes an extensive library of over 80 structured templates across 18 major categories, covering diverse use cases such as poster design, UI mockups, product images, infographics, academic figures, technical architecture diagrams, comics, avatars, process boards, storyboards, IP merchandise creation, and image editing workflows. This makes it a comprehensive tool for developers and AI agent users who need consistent, high-quality image output or prompt-driven image creation in multi-agent setups.

Works with~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/conardli/garden-skills/tree/main/skills/gpt-image-2

Installed? Explore more Image skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →

View original→Browse all skills

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentation

What does GPT Image 2 - Image Generation & Editing Skill do?

A skill for image generation and editing tailored for GPT Image 2. It operates in three modes: (A) Garden local mode, which uses an OpenAI-compatible API to directly generate and save images locally; (B) Host-Native mode, where the skill serves as a prompt engineering guide, handing off the rendered prompt to the host agent's native image tool for output; and (C) Advisor mode, where it degrades into a high-quality prompt consultant when the host lacks any image tool. It covers 18 major categories with 80+ structured templates, spanning posters, UI, products, infographics, academic figures, technical architecture diagrams, comics, avatars, process boards, storyboards, IP merchandise, and editing workflows.

Individual skills in this repo

This repo contains 3 individual skills — each has its own dedicated page.

conardli/kb-retriever

面向本地知识库目录的检索和问答助手。核心流程：(1)分层索引导航 (2)遇到PDF/Excel时必须先读取references学习处理方法 (3)处理文件后再检索。按文件类型组合使用 grep、Read、pdfplumber、pandas 进行渐进式检索，避免整文件加载。用户问题涉及"从知识库目录回答问题/检索信息/查资料"时使用。

conardli/web-design-engineer

Build polished visual web artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use when the user wants a browser-rendered, interactive, or presentational front-end deliverable. Not for back-end, CLI, or non-visual coding tasks.

conardli/web-video-presentation

把一篇文章或口播稿，做成"看起来像视频"的点击驱动 16:9 网页演示，可选合成口播音频。流程：原始文章 → **一次产出**口播稿 + outline 开发计划 → 用户**一次对齐** 5 件事（稿子 / outline / 主题 / 素材 / 开发模式）→ 网页开发（逐章 / 顺序 / 并行）→ 可选音频合成（provider-agnostic：内置 MiniMax mmx-cli + OpenAI TTS，可换 ElevenLabs / edge-tts / Azure / 自带 TTS）。**outline 只规划节奏与信息密度，不规划动画** —— 动画由章节开发时按 PRINCIPLES + ANTI-AI 法则即时设计。每次点击推进口播稿的一个节拍，每一步独占整屏，进度条平时隐藏只在悬浮时出现。适用场景：用网页做视频（动态 PPT 但不像 PPT）、把口播稿 / 文章变成可交互的解说、为 B 站 / YouTube / 视频号录屏教程、做有电影感的产品 / talk demo。本 Skill 沉淀的是设计方法论 + 协作流程 —— 不绑定任何特定样式 / 字体 / 颜色 —— 因此能复用到任意主题与美学。

Related Skills

steipete/songsee

Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.

community

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

community

mattpocock/improve-codebase-architecture

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

community

lobehub/add-provider-doc

Add documentation for a new AI provider — usage docs, env vars, Docker config, image resources.

community

addyosmani/browser-testing-with-devtools

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

community

bytedance/chart-visualization

This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.

community
← More Image skills