Agent
An asset-extraction agent that crops identifiable logos, photos, icons, and illustrations from an existing image and records possible alt text. Alt text is a written description used when an image cannot be seen.
Agent
A code-generation agent that assembles earlier page-analysis results into one complete HTML file using Tailwind CSS. It follows supplied structure, design tokens, assets, and accessibility recommendations rather than inventing new page content.
Agent
A tool that extracts design details from an image, including its main colors, an estimated font category, and spacing measurements. It formats the results as design tokens that can be used with Tailwind CSS.
Agent
A layout-planning agent that turns a visual section map into an HTML page skeleton using Tailwind CSS layout utilities. Tailwind CSS is a system of small reusable classes for arranging and styling web pages.
Agent
A prompt translator for image-generation requests. It turns Korean or abstract descriptions such as “dreamy” or “hip” into specific English visual wording when the request needs more detail.
Agent
A style-memory helper for image generation. It saves visual details such as colors, art style, lighting, composition, texture, and mood, then reuses them when you ask for a series or a similar image.
Agent
An image-observation agent that describes a design’s sections, visible elements, approximate positions, and likely screen size in a fixed JSON format.
Agent
An optional image-review agent that scores one generated image against the user’s stated intent. It rates how well the image matches the request, its composition, color, and technical quality on a 0–10 scale.
Agent
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.
Skill Claude CodeCodex
Convert an image (screenshot, mockup, Figma export) into an HTML page styled with Tailwind CSS. Use this skill whenever the user says "image-to-code …", asks to turn a design image into code, recreate a UI from a screenshot, generate HTML/Tailwind from a mockup, or says things like "이 이미지를 웹페이지로 만들어줘" / "HTML로 바꿔줘" /…
Skill Claude CodeCodex
A landing-page hero image generator for SaaS products and side projects. A hero image is the main visual section at the top of a webpage; this tool leaves part of the image empty so HTML text and a call-to-action can fit beside it.
Skill Claude CodeCodex
An app and website icon set generator. It creates a 1024×1024 master icon, then exports the sizes and layouts needed for iOS, Android adaptive icons, favicons, progressive web apps, and Apple touch icons.
Skill Claude CodeCodex
A logo concept generator that creates symbol ideas with an image model and adds the company name afterward using a real font. It can also turn a selected symbol into an SVG, a scalable vector image.
Skill Claude CodeCodex
A social-preview image generator for blog posts and links. It creates platform-sized background artwork and adds titles and tags afterward with a real font, producing cards for services such as Twitter, Instagram, LinkedIn, and Open Graph previews.
Skill Claude CodeCodex
A presentation-illustration generator for Keynote, PowerPoint, and Google Slides. It creates a matching set of transparent PNG illustrations for section titles, while leaving about 40% of each layout open for slide text.
Skill Claude CodeCodex
A style-board generator for exploring the look and mood of mobile app screens before making a real design in Figma or another design tool.
Skill Claude CodeCodex
Create or edit workspace-bound raster images, including reference-guided generation, precise revisions, variations, and bounded batches. Use when a user asks for an AI-generated bitmap asset or invokes imagine. Do not use for SVG/HTML/code-native graphics, ordinary crop/resize/compression, image-to-code…