GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
GPT-Image2-Skill is a curated prompt library, agentic skill, and command-line tool for generating and editing images with OpenAI's GPT Image 2 model. It integrates directly with Claude Code via the plugin marketplace command, and also supports Codex, OpenClaw, and Hermes Agent through a shared skill folder structure at `~/.codex/skills/gpt-image` or equivalent runtime directories. The prompt library covers specific use cases including research paper figures, UI mockups, game HUDs, anime and manga illustrations, typographic compositions, maps, tattoo designs, and reference-image editing workflows. Installation is handled through `/plugin marketplace add`, `$skill-installer` within Codex, or a cross-agent `npx skills@latest` command. A notable caution in the documentation advises against using GPT Image 2 outputs directly in academic publications, positioning them as workflow sketches or style references rather than finished research assets. The project targets developers, researchers, and designers who work inside skill-capable agent runtimes and want reusable, copy-paste prompt templates for structured image generation tasks.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
git clone https://github.com/wuyoscar/GPT-Image2-Skill ~/.claude/skills/gpt-image2-skill1 items in this repository
Use this skill whenever a user asks to generate, create, draw, render, or edit images with GPT Image 2 / gpt-image-2, text-to-image, reference-image editing, inpainting, posters, typography, Chinese text, UI mockups, diagrams, or gallery prompts. Analyze the user's prompt, search the bundled Reference Gallery/craft files for matching design patterns, confer on direction when useful, then call the packaged `gpt-image` CLI or bundled `scripts/generate.py`. Do not write new image-generation code unless explicitly asked to modify this repo.
Skills overview
What people ask about GPT-Image2-Skill
What is wuyoscar/GPT-Image2-Skill?
+
wuyoscar/GPT-Image2-Skill is skills for the Claude AI ecosystem. GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing It has 5.3k GitHub stars and its last recorded update is dated 2026-09-09.
How do I install GPT-Image2-Skill?
+
You can install GPT-Image2-Skill by cloning the repository (https://github.com/wuyoscar/GPT-Image2-Skill) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is wuyoscar/GPT-Image2-Skill safe to use?
+
Our security agent has analyzed wuyoscar/GPT-Image2-Skill and assigned a Trust Score of 97/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains wuyoscar/GPT-Image2-Skill?
+
wuyoscar/GPT-Image2-Skill is maintained by wuyoscar. The last recorded GitHub activity is dated 2026-09-09, with 3 open issues.
Are there alternatives to GPT-Image2-Skill?
+
Yes. On ClaudeWave you can browse similar skills at /categories/skills, sorted by popularity or recent activity.
Deploy GPT-Image2-Skill to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/wuyoscar-gpt-image2-skill)<a href="https://claudewave.com/repo/wuyoscar-gpt-image2-skill"><img src="https://claudewave.com/api/badge/wuyoscar-gpt-image2-skill" alt="Featured on ClaudeWave: wuyoscar/GPT-Image2-Skill" width="320" height="64" /></a>More Skills
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.