Generate and edit raster images using built-in image tools or a GPT Image CLI fallback.
npx skills add https://github.com/Jensen-Yao/agents-skills --skill imagegen-jensen-yao
Please help me install this Agent Skill. Skill: imagegen Source: https://github.com/Jensen-Yao/agents-skills/tree/main/skills/imagegen Command: npx skills add https://github.com/Jensen-Yao/agents-skills --skill imagegen-jensen-yao
image_gen tool by default, with a guarded scripts/image_gen.py CLI fallback supporting generate, edit, and generate-batch subcommands against GPT Image models. - Transparent-background workflow: Generates subjects on a flat chroma-key background and removes it locally with remove_chroma_key.py, escalating to gpt-image-1.5 --background transparent only after explicit user confirmation. - Structured prompt engineering: Classifies requests into a use-case taxonomy (product-mockup, ui-mockup, photorealistic-natural, precise-object-edit, etc.) and normalizes prompts into a labeled production spec. - Use Case: A user asks for a landing-page hero image of a ceramic mug; the Skill classifies it as product-mockup, builds a structured prompt, generates it with the built-in tool, and copies the final asset into the project workspace. ## Quick Start Ask the agent to generate a product photo of your item on a clean background and save it into your project's assets folder.High-intent search queries and answers about installing and using this skill.
Describe the image you want and the agent uses the built-in image_gen tool by default, no API key required. The Skill structures your prompt with scene, subject, style, and constraints, then saves project-bound outputs into the workspace.
The default path generates the subject on a flat chroma-key background (usually #00ff00) and removes it locally with remove_chroma_key.py to produce an alpha PNG. True native transparency requires the CLI fallback with gpt-image-1.5, which the agent asks about before using.
Use the CLI only when you explicitly ask for CLI/API/model controls or confirm a true-transparency fallback. It requires OPENAI_API_KEY and exposes generate, edit, and generate-batch subcommands with quality, size, mask, and output-format flags.
No, gpt-image-2 does not support background=transparent. The Skill defaults to chroma-key generation plus local removal, and only switches to gpt-image-1.5 with --background transparent after you explicitly confirm that fallback.
gpt-image-2 accepts auto or WIDTHxHEIGHT where edges are multiples of 16, max edge is 3840px, aspect ratio is at most 3:1, and total pixels stay between 655,360 and 8,294,400. Popular sizes include 1024x1024, 1536x1024, 2048x1152, and 3840x2160.
Avoid it when extending an existing SVG/vector icon or logo system, building simple shapes or diagrams better done in HTML/CSS/canvas, or editing an asset that already exists in an editable native format. The Skill targets bitmap output, not code-native visuals.
HainrixzGenerates platform-optimized ad images from campaign briefs and brand profiles.
jangtrinhConvert PDFs, screenshots, and URLs into HTML/CSS design systems.
iterationlayerResize product images to 1200x1200, apply a branded text watermark, and output WebP.
Mathews-TomConvert concept descriptions into self-contained HTML/CSS/SVG visuals and export as PNG or SVG files.