GPT-Image2-Skill
GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
- 5.9k stars
- 470 forks
- 2 open issues
- Language: Python
- License: MIT
- updated
Install
git clone https://github.com/wuyoscar/GPT-Image2-Skill ~/.claude/skills/gpt-image2-skill- Clone the repository into your ~/.claude/skills directory (or copy the skill folder containing SKILL.md).
- Start a new Claude Code session so the skill registry reloads.
- Invoke it by name, or let Claude trigger it automatically when the task matches.
If the repo bundles several skills, copy only the folders you need.
Editor's note
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.
1 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 5.9k GitHub stars and its last recorded update is dated 2026-09-30.
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 2026-09-30, with 2 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.