
Pascal Editor
Lets your AI agent draw rooms, walls and furniture in a 3D home model you can then edit
by Pascal
by Oscar (Yutao) WuSkillMake visuals
Lets your agent make and edit posters, icons and illustrations with OpenAI image models
A skill that lets your agent create and edit images with OpenAI's GPT Image models through a command-line tool, from a description or reference images, saved as PNG, JPEG or WebP. It includes 160+ example prompts.
For Content creatorsDesignersMakers with an OpenAI API key
An open-source skill by Oscar (Yutao) Wu, published on GitHub. It works with OpenAI's image models through your own OpenAI key.
From the project's own repository · 2 images, swipe or use the arrows.
This skill teaches your agent to create and edit images with OpenAI's GPT Image 2 and 2.5 models through a bundled command-line tool. You describe the picture, or give it reference images and an optional mask; it asks which model to use, then saves the finished PNG, JPEG or WebP file. It comes with a gallery of more than 160 example prompts, from posters to diagrams. It suits creators and makers who have an OpenAI API key.
It pairs the image tool with a large, sorted prompt gallery, so your agent can start from a worked example instead of a blank prompt.
Start with the first one: it is a small task you can check easily.
Example prompts written by Agent Flows Hub.
From the creator's documentation.
| Output | What it is | Reads |
|---|---|---|
| Model choice | Asks you to pick Flare, Sunburst or Image 2 when the model is unclear | Your request |
| Prompt gallery | More than 160 numbered example prompts in 31 categories to start from | Skill files |
| New images | Posters, icons, product shots and diagrams made from your description | OpenAI API |
| Reference edits | Restyles or combines images you give it, with an optional mask for one area | OpenAI API |
| Saved files | PNG, JPEG or WebP files written to the path you choose | Your computer |
You need a poster, product shot or diagram and want to describe it in words. The skill asks which GPT Image model to use, runs the bundled command-line tool and reports where the image file was saved.
Notes by Agent Flows Hub (original project name: gpt-image), written from the creator's documentation, not from running it ourselves. gpt-image SKILL.md · GPT Image 2/2.5 Skill README: install and CLI
Tell us what happened. We take a look first; if it needs paid work, you get an estimate before anything starts.