5. Design & Creative

Automatically applies UX psychology principles to optimize landing pages, pricing tables, onboarding flows, and CTAs in UI design.

Provides structured design constraints for creating intuitive user interfaces specifically tailored for agent-based interactions, enhancing usability and consistency.

AI-powered tool for merging 2-8 images with guided composition using Gemini 2.5 Flash via OpenRouter.

Creates and edits visual diagrams including flowcharts and architecture diagrams with XML handling, styling, and PNG export.

Creates, edits, and analyzes PowerPoint presentations (.pptx) including content modification, layout adjustments, and speaker notes.

Offers prompt patterns and parameter guidance for Qwen-Image-Edit to modify photos while preserving identity, changing clothing, and applying style transfers.

Generates comprehensive cultural elements including customs, festivals, cuisine, and rituals for fictional or real groups.

Creates detailed scene-by-scene video specifications for Remotion and After Effects, including timing, audio, sound effects, and animation descriptions.

Converts audio/video content into SRT subtitle files using ElevenLabs Scribe v2 for accurate transcription and captioning.

Provides expert best practices for building animated videos with Remotion, covering React-based synthesis, audio integration, subtitles, and 3D content creation.

Designs complex vibration patterns and subtle audio effects (UI Foley) for mobile interfaces, integrating haptic feedback with UI interactions.

Generates visually appealing infographics from text content, transforming information into clear and engaging visual representations.

Creates cartoon-style infographics for Xiaohongshu (XHS) platform, breaking content into 1-10 visual series upon request.

Trims video segments with compression and audio control options for precise creative video editing tasks.

AI-powered image generation tool supporting multiple models and artistic styles for creative content creation and visual design.

Adds or customizes HeroUI components for consistent, modern UI implementation in web applications using Tailwind CSS.

Generates videos from text or images using AI models like Veo and Sora, enabling text-to-video and image-to-video creation.

Runs visual playtesting via Chrome automation to identify layout, state display, and UX issues missed by API testing.

Delivers Apple-style UI design guidelines with dark mode, blue accents, and minimalist interface for modern application development.

Creates professional, syntax-highlighted code images with customizable themes for documentation, presentations, and social sharing.

Creates high-quality, production-ready web UIs with strong aesthetic direction, covering components, layouts, typography, and motion using modern frontend frameworks.

Extracts audio tracks from video files for use in creative projects or content production.

Automates YouTube video chapter extraction, precise clip generation, and per-chapter SRT subtitle creation using yt-dlp and ffmpeg.

Generates fully illustrated presentation slides with AI, embedding text within images in styles like corporate, minimalist, and kawaii for visual-first decks.