GPT-Image2-Skill

A skill and CLI for generating and editing images with GPT Image 2 and 2.5 plus a library of ready prompts

Skill

Medium risk

We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.

Why this level

  • Calls the paid OpenAI API and spends funds
  • Reads and writes image files in the project
All reasons and checks

wuyoscar/gpt-image2-skill

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/gpt-image2-skill

Detects the agents on your machine, checks the risk and pins the version.

Other ways to install

Assembled automatically, review before installing.

Run in a terminal in the project folder

npx skills add wuyoscar/gpt-image2-skill --skill get-prompt-from-image gpt-image -a claude-code -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 05cb113
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .claude/skills
cp -R "$tmp/skills/get-prompt-from-image" .claude/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .claude/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add wuyoscar/gpt-image2-skill --skill get-prompt-from-image gpt-image -a cursor -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 05cb113
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .agents/skills
cp -R "$tmp/skills/get-prompt-from-image" .agents/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .agents/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add wuyoscar/gpt-image2-skill --skill get-prompt-from-image gpt-image -a github-copilot -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 05cb113
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .github/skills
cp -R "$tmp/skills/get-prompt-from-image" .github/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .github/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add wuyoscar/gpt-image2-skill --skill get-prompt-from-image gpt-image -a codex -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 05cb113
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .agents/skills
cp -R "$tmp/skills/get-prompt-from-image" .agents/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .agents/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add wuyoscar/gpt-image2-skill --skill get-prompt-from-image gpt-image -a gemini-cli -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 05cb113
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .agents/skills
cp -R "$tmp/skills/get-prompt-from-image" .agents/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .agents/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .devin/skills
cp -R "$tmp/skills/get-prompt-from-image" .devin/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .devin/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

Formerly Windsurf.

Run in a terminal in the project folder

npx skills add wuyoscar/gpt-image2-skill --skill get-prompt-from-image gpt-image -a cline -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 05cb113
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .cline/skills
cp -R "$tmp/skills/get-prompt-from-image" .cline/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .cline/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add wuyoscar/gpt-image2-skill --skill get-prompt-from-image gpt-image -a roo -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 05cb113
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .roo/skills
cp -R "$tmp/skills/get-prompt-from-image" .roo/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .roo/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

A fork of Roo Code, same .roo folders.

Run in a terminal in the project folder

npx skills add wuyoscar/gpt-image2-skill --skill get-prompt-from-image gpt-image -a opencode -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 05cb113
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .agents/skills
cp -R "$tmp/skills/get-prompt-from-image" .agents/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .agents/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .agents/skills
cp -R "$tmp/skills/get-prompt-from-image" .agents/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .agents/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/wuyoscar/gpt-image2-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/get-prompt-from-image/ /skills/gpt-image/
git -C "$tmp" checkout 05cb1130bba29e0fc028220376280a2e934a8041
mkdir -p .agents/skills
cp -R "$tmp/skills/get-prompt-from-image" .agents/skills/get-prompt-from-image
cp -R "$tmp/skills/gpt-image" .agents/skills/gpt-image

Commands for macOS and Linux, on Windows run them in Git Bash.

You will need: Node.js

Checked against the repository on Sep 26, 2026, commit 05cb113.

Text for your agent

Install the skill: /plugin marketplace add wuyoscar/gpt_image_2_skill, then /plugin install gpt-image@wuyoscar-skills. Set OPENAI_API_KEY and generate only through the gpt-image CLI with an explicit --model flag.

Other ways from the author
/plugin marketplace add wuyoscar/gpt_image_2_skill
/plugin install gpt-image@wuyoscar-skills

An OPENAI_API_KEY is required.

This is third-party code. Review the repository files before installing.

What it does

The gpt-image skill gives the agent a workflow for generating and editing images with GPT Image 2 and 2.5. It classifies a request into generate, edit, inpaint and multi-reference, helps pick the model and selects a matching case from a prompt gallery. Generation goes only through the bundled CLI; the agent does not write its own API code. There is a separate skill that derives a prompt from an image, plus references on style, typography and image structure.

Who it is for. For designers, marketers and content creators who need images and posters from a brief.

Good fit when

  • You need to generate an image or poster with exact text
  • You need to edit an image by reference or inpaint a region
  • You need to derive a prompt from an existing image

Not a fit when

  • You have no OpenAI key or cannot incur API charges
  • You need a non-OpenAI image model
  • You need video rather than still images

Example request

Make a meetup poster with a centered headline in a minimalist style

Limitations

Requires Python 3.11+ and one of gpt-image, uv or uvx, plus an OPENAI_API_KEY. API calls are paid. OpenAI is not reachable from Russia without a VPN, so availability is marked unknown.

How to disable. Remove the plugin via /plugin uninstall gpt-image@wuyoscar-skills or delete the skill folder and remove the CLI with uv tool uninstall gpt-image-cli.

Security check

  • Calls the paid OpenAI API and spends funds
  • Reads and writes image files in the project

README in short

GPT-Image2-Skill is a prompt gallery, skill and CLI for generating and editing images with OpenAI GPT Image 2 and 2.5. The skill walks the agent through classifying the request, resolving the model, picking a case, calling the CLI without side effects and reporting the result. It bundles a second skill that derives a prompt from an image plus style references. It installs via /plugin, uvx or by copying the folder. MIT licensed.

SKILL.md

---
name: gpt-image
description: "Generate or edit images with GPT Image 2 or 2.5 through the packaged CLI and Reference Gallery. Use for image requests including imprecise 'GPT 2.5' model names, posters, typography, reference edits, and inpainting; resolve the model choice before generation."
compatibility: "Requires Python 3.11+ and either gpt-image, uv, or uvx. CLI/API calls read OPENAI_API_KEY and may incur OpenAI API charges."
---

# gpt-image

Agent runbook for GPT Image 2 / 2.5 generation/editing. Use the prompt library + packaged CLI. Do not reimplement image API code.

FAQ

Which models are supported?

GPT Image 2 and 2.5. The skill resolves the model choice, including loose names like GPT 2.5, before any API call.

Can I skip the plugin?

Yes, you can run the CLI directly with uvx from the repository, but an OpenAI key is required.

Editors’ pick

Skills and CLI from HeyGen: the agent writes HTML compositions and renders them into MP4 videos, captions, motion graphics and decks

SkillMedium risk53.9KRepository stars

Blender MCP

MCP for Blender

Editors’ pick

An MCP server and Blender addon: the agent creates and edits objects, materials and scenes, pulls assets and runs Python in Blender

MCP serverHigh risk29.5KRepository stars
Editors’ pick

Official Remotion skills for making videos in React: compositions, animation, captions, maps and rendering

SkillLow risk4.8KRepository stars

Agentic video studio for Claude Code, Cursor and Codex: script, voiceover, images, stock footage, music, subtitles and render

WorkflowMedium risk61.8KRepository stars
Foxx AIGPT-Image2-Skill

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.