gpt-image-skill
Skill248 starsChanged 4 months agoMITView on GitHub
Generate or edit images when the user names OpenAI, GPT Image, or a gpt-image model. Use the default image skill when no provider is named.
- Reads credentials
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- feiskyer/claude-code-settingstheir own version, first seen Sep 27, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- feiskyer/claude-code-settings★ 1.7ksame name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brainstormingSkill
- claude-skillSkill
- code-simplifierSkill
- deep-researchSkill
- github-fix-issueSkill
- github-review-prSkill
- grill-meSkill
- handoffSkill
- minimax-image-skillSkill
- nanobanana-skillSkill
- youtube-transcribe-skillSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 45
Check that OPENAI_API_KEY is set and, for a custom endpoint, that OPENAI_API_BASE is correct.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GPT Image Skill
Generate or edit images with OpenAI's GPT Image models through the bundled gpt_image.py.
Resolve the skill directory
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.
Requirements
- OPENAI_API_KEY in
~/.gpt-image.envor the shell environment. - OPENAI_API_BASE (optional) for compatible endpoints such as Azure OpenAI or a proxy, in the same places.
- Python dependencies:
python3 -m pip install -r "<skill-dir>/requirements.txt". - Executable:
<skill-dir>/gpt_image.py.
Run it
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.
When a run fails
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.