5. Design & Creative

Creates retro arcade-themed visual prompts to enhance documentation pages with engaging, nostalgic graphics.

Generates visual notes and flowcharts from text input, supporting multiple styles like mind maps and hand-drawn layouts, with image export.

Enables creation, editing, and analysis of Microsoft PowerPoint (.pptx) files, including content modification, layout adjustments, and speaker notes.

Provides practical steps for mastering Text-to-Speech audio, including cleanup, loudness normalization, alignment, and delivery specifications.

Converts text to natural-sounding audio using Google's TTS service, handling long texts via sentence-based chunking and pydub concatenation.

Performs audio track extraction, normalization, mixing, and analysis using FFmpeg for creative media production workflows.

Provides command-line utilities for common image editing tasks including resizing, cropping, blurring, and flipping images.

Converts media files between video containers, audio formats, and codecs using ffmpeg.

Performs basic video editing tasks including cutting, trimming, concatenating, and splitting using FFmpeg.

Applies video filters including scale, crop, watermark, speed, and blur using ffmpeg for creative video editing.

Extracts I-frames from video files to generate thumbnails or key frames for previews and analysis using FFmpeg.

Generates interactive HTML architecture diagrams illustrating data flows, technical components, and deployment structures for system documentation.

Creates interactive HTML flowcharts with decision trees, color-coded stages, arrows, and swimlanes for visual workflow representation.

Generates interactive HTML timelines and project roadmaps with Gantt charts, milestones, and progress indicators for visual project scheduling.

Recommends optimized prompts for the Nano Banana Pro image generation model to create visual content for creative projects like illustrations and media assets.

Processes YouTube and platform videos including download, audio extraction, format conversion, and Whisper transcription for media content creation.

Analyzes images, screenshots, diagrams, and visual content to interpret UI mockups, architecture diagrams, and error screenshots.

Provides intelligent UI/UX design assistance with 67 styles, 96 palettes, and component support for frameworks like React and Tailwind.

Provides standardized design patterns and conventions for creating intuitive command-line interface (CLI) user experiences for the vm0 tool.

Activates the Pickle Rick persona mode in response to explicit user requests, providing a themed conversational experience.

Analyzes UI visual patterns using Gemini AI for design insights, including provider detection and severity assessment.

Provides UI implementation patterns based on design analysis, incorporating Anti-AI design rules and visual verification for improved user interfaces.

Defines schema for UI design style files and reference images, enabling consistent creation and validation of design assets in projects.

Provides a reference for Apple Final Cut Pro's FCPXML format, detailing project structure, timeline, clips, effects, and transitions for project generation and analysis.