OpenAI Imagegen
Official OpenAI skill for image generation, editing, variants, and transparent raster assets.
- Skill Road
- OpenAI Imagegen
OpenAI Imagegen is an official skill for Codex and compatible agents that need to create new raster images or make targeted changes to existing images. The Smithery source originally pointed to the curated imagegen path in the official openai/skills repository. That path is no longer reachable. Checking the current official repository tree identifies the verifiable successor at skills/.system/imagegen. This catalog entry therefore uses the current system path together with OpenAI’s official image-generation documentation. According to the provider, the preferred route is the built-in image tool. A bundled CLI exists only as an explicitly selected fallback and requires locally configured authentication. Those credentials must never be placed in projects, prompts, or catalog copy.
Purpose and audience
The skill is for people who need a bitmap for a website, game, product presentation, prototype, illustration, mockup, cover, infographic, or transparent cutout. It helps the agent first distinguish between creating a new image and editing an existing one. When reference images are supplied, it also establishes whether they provide only style, composition, or mood guidance, or whether one of them is the actual edit target. That distinction protects existing material from unintended changes and makes the requested operation reviewable.
Imagegen is not the right choice when an existing SVG or vector system must be extended exactly, when a logo needs to match an established icon library, or when deterministic output in HTML, CSS, or canvas is sufficient. The skill is not a general image host, an image archive, or a promise of perfect text rendering. For code-native design and exact vector paths, the relevant native technique will usually be more dependable.
Modes and tool selection
The primary source distinguishes a preferred built-in tool mode from an explicit CLI fallback mode. In normal use, the agent should use the built-in image_gen tool and should not switch to a script automatically. If the built-in path is unavailable, the agent should explain that the CLI fallback exists and continue only after the user explicitly chooses it. For CLI use, the source describes generate, edit, and generate-batch operations. The bundled script must not be modified without approval. The skill also explains that built-in output is normally saved under the Codex workspace and that a project-bound asset should be copied or moved into the project afterward.
Before generation, the agent gathers the intended use, asset type, scene, main subject, medium, framing, lighting, palette, materials, exact in-image text, and avoid constraints. A detailed user request should be normalized rather than creatively expanded. For a generic request, the agent may add limited composition or intended-use guidance when it materially helps, but it should not invent unrequested characters, brands, slogans, or objects.
Prompting, variants, and editing
The official guidance recommends a consistent order of scene or backdrop, subject, key details, constraints, and output intent. Short labeled fields are useful for complex requests because they prevent the result from depending on an unstructured mood description. Text inside an image should be supplied verbatim with typography and placement guidance. For edits, the unchanged invariants must be stated explicitly, such as changing only the background while preserving the product and its edges. Each iteration should make one targeted change. That makes it possible to understand whether a difference comes from the new instruction rather than from an unrelated rewrite.
The skill covers photorealistic scenes, product mockups, UI mockups, infographics, illustrations, stylized concepts, and historically grounded scenes. Its editing guidance includes precise object changes, background extraction, lighting or weather changes, style transfer, compositing, and sketch-to-render work. When several variants are needed, the requested differences should be separated clearly. The agent should inspect each result for the subject, style, composition, text accuracy, and preservation of required invariants.
Security, E-E-A-T, and boundaries
This description is grounded in the official OpenAI source at skills/.system/imagegen and the official OpenAI image-generation documentation. According to the provider, the distinction between the built-in tool and an explicitly requested CLI matters; it is not a guarantee of availability, quality, or rights clearance. Images may contain people, brands, confidential references, or copyrighted elements. Before publication, a person should verify that the inputs and outputs may be used, that any required disclosure is present, and that the image does not create misleading or sensitive impressions. A generated image is not evidence that a depicted scene is true.
Local file paths, output directories, and reference images can disclose sensitive information. Unneeded drafts should be retained or deleted under controlled rules. Existing project assets should not be overwritten unless replacement was explicitly requested. Tokens, keys, and other secrets must never be written into examples or output files. A compatible agent may add its own logging, model route, or network services depending on the environment, so the responsible team must review the actual data flow, permissions, and retention separately. Imagegen accelerates visual work, but it does not replace editorial, legal, trademark, or subject-matter approval.
Installation instructions
OpenAI Imagegen is an official skill from the public openai/skills repository, located under skills/.system/imagegen. A skill in this sense is not a standalone application but a structured instruction file in SKILL.md format that tells an AI coding assistant such as Codex or Claude Code when and how to generate or edit images. According to the provider, the skill activates whenever a project benefits from AI-generated raster visuals, for example website assets, game assets, UI mockups, product mockups, wireframes, logo design, photorealistic images, or infographics. It is explicitly not meant for purely vector-based or code-native graphics, such as SVG icons that are maintained directly within an existing icon system.
Two operating modes
According to the provider, the skill defines exactly two modes. The preferred default mode uses the coding agent's built-in image generation tool and requires no separate OpenAI API key, since costs are covered through the user's existing subscription. The second mode, explicitly activated only on an explicit user request, calls a bundled command-line script that offers subcommands for generating, editing, and batch-processing images. This CLI fallback requires its own API key and, per the instructions, is never switched to automatically in place of the default mode, even if the built-in path fails; instead the assistant is supposed to inform the user first and ask for explicit consent.
Requirements
Using the skill requires an environment that supports the Agent Skills format, such as Codex or compatible Claude tools, where skills are stored as local directories containing a SKILL.md file. The default mode needs no separate programming key, since it relies on the agent's built-in tool. Only someone who explicitly wants to use the CLI fallback needs to set an environment variable containing a valid OpenAI API key.
Step 1: Installation and file locations
The skill can be downloaded through common skill installers from the openai/skills repository, for example via a command-line call that installs only the imagegen skill specifically. After downloading, the SKILL.md file typically lives in the local skills directory of the project or user profile. According to the instructions, the bundled image-generation script should not be modified on one's own; if something is missing, the assistant is supposed to ask first rather than improvise its own solution.
Security, storage locations, and limits
In the default mode, according to the provider, the coding agent first stores generated images in its own internal directory rather than automatically in the system's temp folder. Images actually meant for use in the project must then be deliberately moved or copied into the workspace; pure preview or brainstorming images, on the other hand, can remain at their original location. Existing files are not overwritten without being asked; instead, per the guidance, a new filename with a version suffix is assigned. Anyone using the CLI fallback should keep in mind that image prompts and any uploaded reference images are transmitted to OpenAI once an API key is in use.
Practical benefit
In practice, the skill is well suited to quickly producing visual placeholders, concept images, or finished assets right inside the development workflow, without switching context or opening a separate image tool. The clear split between default and fallback modes ensures that extra costs or programming keys only come into play when actually wanted. The limit is reached where existing vector graphics or icon systems need ongoing maintenance, since the skill, by its own description, is not intended for that.
- Provider
- OpenAI
- License
- Apache-2.0
- Last reviewed
- 09.09.2026
Repository and documentation
Categories
Compatible with
Related guides
Guides and background related to this entry.