Agent skill · creative production · aradotso
gpt-image-2-api-prompts
gpt-image-2-api-prompts — an agent skill for coding agents.
Why this skill is useful
Adds a callable skill and multiple executable scripts for image generation using the GPT-Image-2 API that aren't widely available in public documentation.
What it needs
Requires node, python installed locally. Requires evolink account access. About 6k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
bash npx evolink-gpt-image -y bash export EVOLINKAPIKEY="yourapikeyhere" bash pip install openai requests python-dotenv python import os import requests apikey = os.environ["EVOLINKAPIKEY"] response = requests.post( "https://api.evolink.ai/v1/images/generations", headers={ "Authorization": f"Bearer {apikey}", "Content-Type": "application/json", }, json={ "model": "gpt-image-2", "prompt": "A beautiful colorful sunset over the ocean", "n": 1, "size": "1024x1024", }, ) data = response.json() imageurl = data["data"][0]["url"] print(imageurl) python import os from openai import OpenAI client = OpenAI( apikey=os.environ["EVOLINKAPIKEY"], baseurl="https://api.evolink.ai/v1", ) response = client.images.generate( model="gpt-image-2", prompt="Hyper-realistic miniature diorama product advertisement, luxury skincare bottle, tiny figurine workers on scaffolding, warm beige palette, studio photography, 8K", n=1, size="1024x1024", quality="hd", ) print(response.data[0].url) python import os import requests from pathlib import Path from openai import OpenAI client = OpenAI( apikey=os.environ["EVOLINKAPIKEY"], baseurl="https://api.evolink.ai/v1", ) def generateandsave(prompt: str, outputpath: str, size: str = "1024x1024") -> str: response = client.images.generate( model="gpt-image-2", prompt=prompt, n=1, size=size, quality="hd", ) imageurl = response.data[0].url imgdata = requests.get(imageurl).content Path(outputpath).writebytes(imgdata) print(f"Saved to {outputpath}") return imageurl generateandsave( prompt="Cinematic hero image of a gourmet cheeseburger on dark stone surface, glossy brioche bun, melted cheese, warm side light, shallow depth of field, premium food commercial style", outputpath="burgerhero.jpg", size="1792x1024", ) python import os import json import time import requests from openai import OpenAI client = OpenAI( apikey=os.environ["EVOLINKAPIKEY"], baseurl="https://api.evolink.ai/v1", ) def batchgenerate(prompts: list[dict], delay: float = 1.0) -> list[dict]: """ p …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/gpt-image-2-api-prompts