imagegen

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

Updated Aug 19, 2026
One-click install
npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill imagegen-jakubbartnik
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: imagegen
Source: https://github.com/jakubbartnik/honey-barrel-finale/tree/main/honey-barrel-finale/workspace/openclaw-config/agents/main/agent/codex-home/skills/.system/imagegen
Command: npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill imagegen-jakubbartnik

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Creating bitmap assets like photos, illustrations, product mockups, sprites, and transparent cutouts normally requires design tools or manual API scripting; this Skill lets an AI agent generate and edit those images directly within a project workflow. ## Core Features & Use Cases - Built-in image generation and editing: Uses the built-in image_gen tool by default for new images, edits, and simple transparent-background requests without requiring an API key. - Fallback CLI mode: A bundled scripts/image_gen.py CLI exposes generate, edit, and generate-batch subcommands with explicit control over model, quality, size, masks, and output paths when the user opts in. - Transparent-background workflow: Generates subjects on a flat chroma-key background and removes it locally with remove_chroma_key.py, with a confirmed gpt-image-1.5 fallback for true native transparency. - Use Case: A developer building a landing page asks for a hero image of a ceramic mug; the Skill generates it, validates the result, and saves the final PNG into the project workspace. ## Quick Start Ask the agent to generate a hero image of your product for the landing page 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 with this Skill?▼

Describe the image you want in natural language and the built-in image_gen tool generates it by default, with no API key required. The Skill structures your prompt with scene, subject, style, and constraint fields, then saves the result into your workspace if it is project-bound.

How do I create an image with a transparent background?▼

The default path generates the subject on a flat chroma-key background and removes it locally with the remove_chroma_key.py helper to produce an alpha PNG. For complex subjects like hair, glass, or smoke, the Skill asks before falling back to CLI gpt-image-1.5 with background=transparent.

When should I use the CLI fallback instead of the built-in image tool?▼

Use the scripts/image_gen.py CLI only when you explicitly need API-level controls such as model selection, quality, masks, output formats, or batch generation from a JSONL file. It requires OPENAI_API_KEY and network access, and gpt-image-2 is the default model.

Does gpt-image-2 support transparent backgrounds?▼

No, gpt-image-2 does not support the background=transparent parameter. Transparent output either uses the built-in chroma-key removal workflow or, after user confirmation, the CLI with gpt-image-1.5 and png or webp output format.

When should I not use AI image generation for an asset?▼

Avoid it when the task is better served by editing existing SVG or vector assets, extending an established icon or logo system, or building the visual directly in HTML, CSS, or canvas. The Skill is intended for bitmap output, not code-native graphics.