$ ~/registry/skill/openai-system-imagegen

SKILL

imagegen

Name: imagegen
Author: OpenAI

Generate or edit bitmap images for illustrations, photos, textures, mockups, and cutouts.

Stars

★ 23,132

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 22.0k

Summary

This skill appears to be a prompt-oriented wrapper for image generation, with no required key or declared remote endpoint in the default mode, and it comes from a high-star open-source GitHub repository, so the overall risk is low. Caution is still warranted because the docs mention an optional CLI fallback using OPENAI_API_KEY and local saving/moving of generated images.

CredentialsCaution

The objective metadata says no key is needed in the default mode, but the README states that the explicit CLI fallback requires OPENAI_API_KEY. No extra high-sensitivity credential request or suspicious collection behavior is shown; the main concern is standard protection of the API key if CLI mode is used.

Network egressLow risk

No remote endpoint is declared in the materials, and the system check also marks host as none. While image generation may rely on built-in platform services in some implementations, the provided materials do not show any red flag of sending data to unknown, unrelated, or third-party endpoints.

Code executionCaution

As a skill, it primarily uses the built-in image_gen tool by default; the README also describes an explicit CLI fallback via `scripts/image_gen.py`. This implies normal tool-level execution capability, but there is no sign of requesting system privileges beyond its stated purpose or any suspicious execution behavior.

Data accessCaution

The README explicitly says generated images are saved under `$CODEX_HOME/generated_images/...` and may be moved or copied into the workspace on user request. This is standard local file read/write behavior needed for an image skill, with no indication of excessive permissions or access to unrelated data.

Supply chainLow risk

The source is the open-source GitHub repository `openai/skills`, and the system marks it as open-source with strong community adoption (~22k stars), which materially lowers supply-chain risk. The license and maintenance status are unclear and worth verifying, but the current materials do not justify a high-risk rating.

Recommendations

Prefer the built-in mode by default; only enable the CLI fallback when it is explicitly needed and understood.
If CLI mode is used, protect OPENAI_API_KEY with least-privilege handling and avoid storing it in the repo or logs.
Review generated image paths in `$CODEX_HOME` and the workspace to avoid overwriting assets or committing unwanted outputs.
Before production use, additionally verify the repository license, recent maintenance activity, and the actual implementation of `scripts/image_gen.py`.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "imagegen" skill from askskill:
1. Download https://raw.githubusercontent.com/openai/skills/main/skills/.system/imagegen/SKILL.md
2. Save it as ~/.claude/skills/imagegen/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Image Generation Skill

Generates or edits images for the current project (for example website assets, game assets, UI mockups, product mockups, wireframes, logo design, photorealistic images, or infographics).

Top-level modes and rules

This skill has exactly two top-level modes:

Default built-in tool mode (preferred): built-in image_gen tool for normal image generation and editing. Does not require OPENAI_API_KEY.
Fallback CLI mode (explicit-only): scripts/image_gen.py CLI. Use only when the user explicitly asks for the CLI path. Requires OPENAI_API_KEY.

Within the explicit CLI fallback only, the CLI exposes three subcommands:

generate
edit
generate-batch

Rules:

Use the built-in image_gen tool by default for all normal image generation and editing requests.
Never switch to CLI fallback automatically.
If the built-in tool fails or is unavailable, tell the user the CLI fallback exists and that it requires OPENAI_API_KEY. Proceed only if the user explicitly asks for that fallback.
If the user explicitly asks for CLI mode, use the bundled scripts/image_gen.py workflow. Do not create one-off SDK runners.
Never modify scripts/image_gen.py. If something is missing, ask the user before doing anything else.

Built-in save-path policy:

In built-in tool mode, Codex saves generated images under $CODEX_HOME/* by default.
Do not describe or rely on OS temp as the default built-in destination.
Do not describe or rely on a destination-path argument (if any) on the built-in image_gen tool. If a specific location is needed, generate first and then move or copy the selected output from $CODEX_HOME/generated_images/....
Save-path precedence in built-in mode:
1. If the user names a destination, move or copy the selected output there.
2. If the image is meant for the current project, move or copy the final selected image into the workspace before finishing.
3. If the image is only for preview or brainstorming, render it inline; the underlying file can remain at the default $CODEX_HOME/* path.
Never leave a project-referenced asset only at the default $CODEX_HOME/* path.
Do not overwrite an existing asset unless the user explicitly asked for replacement; otherwise create a sibling versioned filename such as hero-v2.png or item-icon-edited.png.

Shared prompt guidance for both modes lives in references/prompting.md and references/sample-prompts.md.

Fallback-only docs/resources for CLI mode:

references/cli.md
references/image-api.md
references/codex-network.md
scripts/image_gen.py

When to use

Generate a new image (concept art, product shot, cover, website hero)
Generate a new image using one or more reference images for style, composition, or mood
Edit an existing image (inpainting, lighting or weather transformations, background replacement, object removal, compositing, transparent background)
Produce many assets or variants for one task

When not to use

Extending or matching an existing SVG/vector icon set, logo system, or illustration library inside the repo
Creating simple shapes, diagrams, wireframes, or icons that are better produced directly in SVG, HTML/CSS, or canvas
Making a small project-local asset edit when the source file already exists in an editable native format
Any task where the user clearly wants deterministic code-native output instead of a generated bitmap

Decision tree

Think about two separate questions:

Intent: is this a new image or an edit of an existing image?
Execution strategy: is this one asset or many assets/variants?

Intent:

If the user wants to modify an existing image while preserving parts of it, treat the request as edit.
If the user provides images only as references for style, composition, mood, or subject guidance, treat the request as generate.
If the user provides no images, treat the request as generate.

Built-in edit semantics:

…

View full docs ↗