Skill UI

A comprehensive skill for creating, editing, and automating vector graphics and technical diagrams using LibreOffice Draw. It supports the native ODG format and facilitates seamless format conversion between ODG, SVG, PDF, PNG, and JPG. Ideal for generating flowcharts, organizational charts, and technical schematics, and for batch processing graphics operations via command-line or Python UNO scripting.

This skill provides AI-powered capabilities for advanced image manipulation. It specializes in style transfer, allowing users to apply the aesthetic characteristics of one image to another, and object removal, enabling seamless retouching by eliminating unwanted elements. It is essential for designers, photographers, and artists requiring high-quality, creative photo editing and visual enhancement.

Edits Chinese articles, comments, and documents to remove clichés, repetitions, and templated expressions, making text more natural while preserving facts, certainty, and author voice. Suitable for polishing existing text, not for authorship detection or guaranteeing passage through AI detectors.

This intelligent studio acts as a visual creative director, automatically routing image requests to the optimal specialized AI model. It handles hyper-realistic portrait generation (for influencers/professional photos) and advanced artistic creation, illustration, and photo manipulation (upscale, inpainting, background removal). Use it for professional content creation requiring specialized visual expertise.

This expert acts as a Design Systems Lead and Prompt Engineer for creating high-fidelity, consistent UI designs. It transforms vague ideas into structured specifications by enhancing prompts with professional UI/UX terminology, synthesizing design system source files, and managing multi-step generation and editing workflows using the Stitch MCP.

Expert skill for creating, editing, and optimizing marketing images using AI generation models (Flux, Midjourney, Ideogram, Gemini, etc.) and design tools. Covers blog heroes, social graphics, product mockups, banners, and brand assets with best practices for prompts, tool selection, and optimization.

This powerful script uses Nano Banana models to facilitate advanced image creation and manipulation. Users can generate high-quality images from simple text prompts, perform detailed image edits (inpainting/outpainting), or combine multiple images into a single collage. It supports various resolutions and aspect ratios, making it ideal for artists, designers, and anyone requiring advanced visual content generation.

Use this powerful skill to perform advanced, multi-modal video generation and editing using the official google-genai SDK. Capabilities include generating realistic videos from text prompts (Text-to-Video), animating scenes from a single input image (First-Frame-to-Video), and applying style or character references from images. It also supports complex video refinement, inpainting, and optimizing source footage for professional creative workflows.

Creative-direction layer for music videos and short-form edits in the angelcore, cloud-trance, and hyperpop family. Provides named-genre aesthetic vocabulary, mood/color/light systems, beat-synced editing grammar, and a pipeline for coherent AI b-roll and distribution.

This comprehensive guide details the workflow for using built-in AI tools to create original artwork, product visuals, and diagrams, and to intelligently edit existing images. It emphasizes crafting detailed art-direction prompts, managing image input paths, and maintaining consistency across multi-turn editing sessions.

This skill establishes a crucial, one-time connection to the user's personal Cognitum Music account. It requires the user to mint a Personal Access Token (PAT) and register the Music Connect (MCP) server. This setup must be run before any music generation, editing, or production tools can be accessed, ensuring the session is properly authenticated for music tasks.

Provides domain knowledge for compiling character/scene/prop creative settings into executable image generation prompts. Covers reference board layouts (character identity boards, sequence keyframes, environment study boards, prop study boards), composition and camera language, avoiding image moderation false positives, entity continuity, and cross-variant derivative design based on the main image. Not for video prompt compilation, pure material editing, or evaluating generated outputs.