Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

GPT Image Skill

Lets Claude Code generate and edit images through OpenAI's GPT Image API with a bundled Python script.

Image & VideoBeginner★ 1,653⑂ 238AI score 9/10Last updated: Aug 13, 2026

What it does

  • Runs a bundled gpt_image.py script to generate images via the OpenAI GPT Image API (gpt-image-2, 1.5, 1, 1-mini).
  • Supports an edit mode that takes up to three reference images for editing or compositing.
  • Exposes size (square/portrait/landscape), quality, output format (png/jpeg/webp), transparent background, and batch count options.
  • Trigger is deliberately narrow: only fires when the user names OpenAI/GPT as the provider, and it explicitly tells the model to draw diagrams with Mermaid instead.

Who it's for

  • Developers and designers who already hold an OpenAI API key and want images straight from the terminal.
  • Content creators iterating on logos, mascots, thumbnails, and social assets.
  • Teams routing through compatible endpoints such as Azure OpenAI or a proxy via OPENAI_API_BASE.

Example uses

  1. "Use OpenAI to make a minimalist tech startup logo, 1024x1024, high quality" → --size 1024x1024 --quality high --output logo.png.
  2. "With gpt image, add a rainbow to the sky in photo.png" → edit --input photo.png.
  3. "Cartoon cat mascot on a transparent background" → --background transparent --format png.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/feiskyer/claude-code-settings/HEAD/skills/gpt-image-skill/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/gpt-image-skill folder from the GitHub repo feiskyer/claude-code-settings into my ~/.claude/skills/gpt-image-skill/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/feiskyer/claude-code-settings.git /tmp/ccs && mkdir -p ~/.claude/skills && cp -r /tmp/ccs/skills/gpt-image-skill ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Clone the repository: git clone https://github.com/feiskyer/claude-code-settings.git
  2. Copy the skill into place: mkdir -p ~/.claude/skills && cp -r claude-code-settings/skills/gpt-image-skill ~/.claude/skills/
  3. Install Python dependencies: python3 -m pip install -r ~/.claude/skills/gpt-image-skill/requirements.txt
  4. Add your key: echo 'OPENAI_API_KEY=sk-...' > ~/.gpt-image.env (or export OPENAI_API_KEY=sk-...).
  5. If you use a custom endpoint, add OPENAI_API_BASE=... to the same file.
  6. Restart Claude Code and ask with the provider named, e.g. "generate an image with OpenAI of a mountain lake at sunset".
View source on GitHub ↗License: MIT