Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →feiskyer/gpt-image-skill
Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT as the provider: "gpt image", "openai image", "generate image with openai", "用 openai 画图", "用 GPT 生成图片". For generic image requests without a provider, use nanobanana-skill instead.
Passed 5 of 12 test cases with the skill, and 4 of 12 without it.
3 fixed7 passed either way13 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
In which environment file under the user's home folder does the tool look for OPENAI_API_KEY?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies ~/.gpt-image.env as the file location. | Missed | Passed |
The instructions your model reads when the skill loads.
Generate or edit images with OpenAI's GPT Image models through the bundled gpt_image.py.
Before running any command, resolve the absolute directory containing this SKILL.md and refer to it as <skill-dir>. Never assume the current working directory is the skill directory. Keep user input and output paths relative to the user's working directory unless the user requests another location.
~/.gpt-image.env or the shell environment.python3 -m pip install -r "<skill-dir>/requirements.txt".<skill-dir>/gpt_image.py.Generate:
python3 "<skill-dir>/gpt_image.py" --prompt "Modern minimalist logo for a tech startup" \
--quality high --background transparent --output "logo.png"
Edit or combine references:
python3 "<skill-dir>/gpt_image.py" edit --prompt "Add a rainbow in the sky" \
--input photo.png --output "photo-with-rainbow.png"
edit accepts several --input files to composite multiple references into one image.
Options live on the subcommands, so read them with generate --help or edit --help — the bare python3 "<skill-dir>/gpt_image.py" --help only lists the two modes. That is where the current --model, --size, --quality, --format, --background, and --n values are; every one has a working default, so pass only what the request actually constrains. Parent directories in the output path are created automatically, and an omitted --format is inferred from the .png, .jpg/.jpeg, or .webp extension, defaulting to PNG.
Report the saved path when the run completes.
Check that OPENAI_API_KEY is set and, for a custom endpoint, that OPENAI_API_BASE is correct; confirm input images exist and are readable, the output directory is writable, and the model name is valid. Do not report success unless an image was saved locally.
test cases passed, vs 4 / 12 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.