Skill UI

This advanced skill is designed to generate high-quality, publication-ready academic illustrations and diagrams. It utilizes a sophisticated, multi-stage iterative workflow involving Claude for planning, layout optimization, and strict visual review, combined with a dedicated local Codex app-server bridge for native image rendering. The process ensures that generated figures meet the rigorous aesthetic and structural standards required for top-tier conferences and journals (e.g., CVPR, NeurIPS).

This skill prevents AI coding agents from generating generic interfaces by leveraging over 800,000 real web and iOS screens. It helps define design contracts, cover required states, and enforce quality gates during design, implementation, or review. Compatible with agents like Cursor, Copilot, and Claude Code, it ensures product-specific UIs grounded in actual user experience rather than hallucinated patterns.

Generate images with Google Gemini's image model straight from a Claude Code session. Create UI placeholders, icons, documentation illustrations, diagrams and concept visuals, saved locally as PNG files with a returned file path.

Install and run the pinned, official AI Logo Maker package from Beatra to turn a brand name, industry, or reference image into logo concepts inside Claude Code, Codex, or Cursor; includes digest verification, safety review, and paid hosted rendering.

Install the pinned Beatra AI Music Generator package to turn themes, lyrics, or reference audio into songs, instrumentals, and soundtracks inside Claude Code, Codex, or Cursor, using paid hosted rendering with verified download and review steps.