AI-generated frontend work can look generic and miss responsive states. This skill gives Claude, Codex, and Claude Code opinionated UI rules for sharper React and Tailwind outputs.

AI-generated interfaces often look generic or miss production details. This skill gives Claude, Codex, and Claude Code strict design and frontend guardrails.

Teams need brand concepts that look coherent before they invest in a full identity system. This skill guides Claude, Codex, and Claude Code to create polished brand-kit boards with logos, palettes, mockups, and visual rules.

Creating polished images and consistent visual sets requires detailed prompts and repeated API work. This skill prepares requests, calls Seedream, and downloads the results.

Scientific teams need clear diagrams without slow manual drawing. This skill turns detailed prompts into reviewed schematics, pathways, flowcharts, and architecture figures.

Creating polished visual assets can be slow when users must switch tools. This skill lets Claude, Codex, and Claude Code generate or edit images through OpenRouter models from text prompts.

Finished interfaces often need small visual adjustments before release. This skill guides Claude, Codex, and Claude Code to refine clarity while preserving the design.

Pencil designs often lose detail when developers translate them by eye. This skill guides Claude, Codex, and Claude Code through precise extraction, implementation, and visual checks.

Product teams often overload success states with unclear next steps. This skill turns user intent into scoped, prioritized UI actions after a meaningful outcome.

Design handoff often breaks architecture, tokens, and accessibility. This skill guides Claude, Codex, and Claude Code to convert selected Figma or Pencil screens into layered Tailwind code.

Next.js teams often miss favicon, PWA, and social image requirements. This skill audits the project, prepares exact asset specs, and wires generated files into App Router conventions.

Turning long content into social image cards is slow and inconsistent. This skill plans Xiaohongshu-style infographic series with styles, layouts, prompts, and output paths.

Turning long content into a consistent visual deck takes planning and prompt writing. This skill creates a structured outline, slide prompts, and generated slide images.

Turning notes or reports into a clear visual can take many design decisions. This skill analyzes content, recommends layouts and styles, and prepares an image prompt for Claude, Codex, or Claude Code workflows.

Image prompts often need provider setup, sizes, and repeatable output paths. This skill runs an API-based generator with aspect ratio, quality, and reference image options.

Connects AI workflows to Gemini Web generation without a separate API integration. Produces text, images, vision responses, and multi-turn results from a command-line interface.

Article creators need consistent cover visuals without manually designing every composition. This skill guides image prompts across style, color, layout, text, mood, and aspect ratio choices.

Large image files slow uploads, pages, and storage workflows. This skill compresses supported images into WebP, PNG, or JPEG files with configurable quality and batch processing.

Educational topics can be difficult to explain with plain text and generic visuals. This skill turns source material into structured comic plans, image prompts, and export-ready pages.

Article authors often know their message but lack a clear visual plan. This skill finds useful illustration points and prepares consistent raster image generation prompts.