Skip to content
appsgit

Get Prompt From Image

Get Prompt From Image is an agent skill (a SKILL.md file) from wuyoscar/GPT-Image2-Skill. Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. It works with Claude Code and Codex and has 5,637 GitHub stars across a repository of 2 listed skills.

github.com/wuyoscar/GPT-Image2-Skill/skills/get-prompt-from-image (opens in a new tab)

View on GitHub (opens in a new tab)

Add this skill

Claude

This repository is a Claude Code plugin marketplace. In Claude Code:

/plugin marketplace add wuyoscar/GPT-Image2-Skill
/plugin install gpt-image@wuyoscar-skills

In the Claude apps, zip the get-prompt-from-image folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).

ChatGPT / Codex

Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:

git clone --depth 1 https://github.com/wuyoscar/GPT-Image2-Skill.git
cp -r GPT-Image2-Skill/skills/get-prompt-from-image .agents/skills/get-prompt-from-image   # repo; ~/.agents/skills for all projects

Standalone skills also load in the ChatGPT desktop app.

Cursor

Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:

git clone --depth 1 https://github.com/wuyoscar/GPT-Image2-Skill.git
cp -r GPT-Image2-Skill/skills/get-prompt-from-image .cursor/skills/get-prompt-from-image   # project; ~/.cursor/skills for all projects

Source (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)

What this skill does

Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references. Do not use for requests that only require OCR or an ordinary image description.

When it triggers

  • Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references.
  • use for requests that only require OCR or an ordinary image description.

More skills in wuyoscar/GPT-Image2-Skill

2 skills are listed from this repository.

Similar skills

More design & frontend skills

All Design & frontend

FAQ

Get Prompt From Image FAQ

Still curious? Email info@appsgit.com.

What is the Get Prompt From Image skill?

Get Prompt From Image is an agent skill (a SKILL.md file) from wuyoscar/GPT-Image2-Skill. Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. It works with Claude Code and Codex and has 5,637 GitHub stars across a repository of 2 listed skills. Its SKILL.md lives at github.com/wuyoscar/GPT-Image2-Skill/skills/get-prompt-from-image.

How do I install the Get Prompt From Image skill?

In Claude Code, run /plugin marketplace add wuyoscar/GPT-Image2-Skill and then /plugin install gpt-image@wuyoscar-skills. For Codex or Cursor, copy the get-prompt-from-image folder into .agents/skills/ or .cursor/skills/.

Is the Get Prompt From Image skill free?

Yes. The repository is open source under the MIT license.

Is Get Prompt From Image maintained?

The repository's most recent commit was on Sep 30, 2026. Its latest release is v0.2.0. appsgit only lists skills from repositories with a commit in the last six months.