skills.rest
zniihgnexy
zniihgnexyCOMMUNITY
Explore all skills by this author →
GitHub

imagegen

Generate and edit raster images using GPT Image models via a built-in tool or CLI.

Updated Apr 1, 2026
Search Tags:#prompt engineering#OpenAI#image generation#image editing#gpt-image#batch generation#raster assets
One-click install
npx skills add https://github.com/zniihgnexy/vid_tokenizer --skill imagegen-zniihgnexy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: imagegen
Source: https://github.com/zniihgnexy/vid_tokenizer/tree/main/.ds/codex-home/skills/.system/imagegen
Command: npx skills add https://github.com/zniihgnexy/vid_tokenizer --skill imagegen-zniihgnexy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve? Creating bitmap visuals such as photos, illustrations, product mockups, sprites, and transparent-background cutouts normally requires design tools or manual asset production; this Skill generates or edits those raster images directly from prompts and reference images. ## Core Features & Use Cases - Image generation and editing: Create new images from text prompts or edit existing images with inpainting, background replacement, object removal, lighting changes, and style transfer. - Dual execution modes: Uses the built-in image_gen tool by default, with an explicit scripts/image_gen.py CLI fallback supporting generate, edit, and generate-batch subcommands for JSONL batch jobs. - Structured prompt workflow: Provides a use-case taxonomy, shared prompt schema, and copy/paste recipes for website assets, game assets, wireframes, and logos. - Use Case: A developer building a landing page asks for a hero image of a ceramic mug; the Skill classifies it as product-mockup, builds a structured prompt, generates the image, and saves the final asset into the project workspace. ## Quick Start Ask the assistant to generate a wide hero image of a ceramic coffee mug in clean product photography style with no text or watermark, and save it into the project workspace.

Frequently Asked Questions about imagegen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an image from a text prompt?▼

Describe the subject, style, composition, and constraints in your request, and the built-in image_gen tool generates the bitmap by default. The Skill structures your prompt into a labeled spec covering use case, scene, lighting, and avoid items before generation.

How do I edit an existing image with AI?▼

Provide the image and state exactly what to change, such as replacing only the background while keeping the subject unchanged. Local files are first loaded with the view_image tool so they enter conversation context, then the built-in edit flow applies the change.

When should I use the image_gen.py CLI instead of the built-in tool?▼

Use the CLI fallback only when you explicitly want file-path control, masks, input_fidelity, quality settings, or JSONL batch generation. It requires OPENAI_API_KEY and network access, while the built-in tool does not.

Can I generate many image assets in one batch?▼

Yes. With the built-in tool, issue one image_gen call per asset or variant. In explicit CLI mode, the generate-batch subcommand runs many prompts concurrently from a JSONL file with per-job overrides for size, quality, and output format.

When should I not use AI image generation for visuals?▼

Avoid it when extending an existing SVG icon set, logo system, or illustration library, or when simple shapes and diagrams are better built directly in SVG, HTML/CSS, or canvas. The Skill is for bitmap assets, not code-native vector output.

Why does the image generation CLI fail with an API key error?▼

The CLI requires OPENAI_API_KEY set as an environment variable for live API calls; dry-run mode works without it. Create a key in the OpenAI platform UI, export it in your shell, and confirm network access is enabled in your sandbox configuration.

Related Skills

Explore More Design & Creative Skills→
Pika-LabsPika-Labs
38

build-a-brand

Build a complete brand identity and 15-page brand guidelines PDF.

Official
Advanced
AshesOfTheUndeadAshesOfTheUndead

image-generation

Generates images from text prompts via z-ai- web-dev-sdk API with backend-only execution.

Community
Advanced
iterationlayeriterationlayer
2

image-resize-watermark-convert

Resize product images to 1200x1200, apply a branded text watermark, and output WebP.

Official
Intermediate
yejuneyejune

do-tool-svg

Create, optimize, and animate SVG graphics using SVGO and native features.

Community
Advanced