Skill UI

This skill provides access to a comprehensive, high-quality icon library designed for modern UI/UX systems. It ensures superior visual consistency across digital products by offering multiple premium styles (Linear, Bold, Two-tone). Users can find existing icons or leverage the integrated AI generator to create unique, perfectly styled custom icons, elevating the design professionalism beyond standard generic sets.

A comprehensive skill for generating multimodal media content using fal.ai models. It supports text-to-image (Nano Banana), text/image-to-video (Veo, Kling, Seedance), and text/video-to-audio (CSM-1B, ThinkSound). Use this tool for any creative project requiring high-quality generated images, videos, or sound effects.

NOTE: This skill is DEPRECATED and should no longer be used for creating new posters. The functionality has been superseded by /paper-poster-html. Users must immediately migrate to the new HTML/CSS pipeline for accurate, measurement-gated poster generation, avoiding the legacy LaTeX flow.

This skill transforms written content, such as articles and reports, into engaging, two-host conversational podcast audio. It first structures the content into a detailed JSON script (dialogue format) and then uses advanced Text-to-Speech synthesis to generate the final MP3 file. Supports both English and Chinese languages, making content accessible for audio-only listening.

This skill acts as an elite Art Director for generating premium, highly actionable, and structurally sound frontend design references. It moves beyond generic AI aesthetics by enforcing principles like strong hierarchy, generous spacing, and image-led composition. Ideal for creating realistic, development-ready concepts for landing pages, hero sections, and multi-section websites.

This skill provides a comprehensive guide on programmatically interacting with the Lucidchart API. It demonstrates how to create new documents, add structured shapes and connecting lines using standard import formats, and finally export the finished diagram (e.g., as PNG). It is ideal for automating the visualization of architecture diagrams, system workflows, or business processes within an application.

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.

Generates structured DESIGN.md files that serve as a single source of truth for AI-powered screen generation (Google Stitch). This skill translates complex, anti-generic design directives into precise semantic rules, covering typography, color calibration, motion physics, and layout principles to enforce a premium, high-agency UI/UX standard. It ensures outputs are sophisticated and avoid common AI design clichés.

A comprehensive skill that automates the entire process of creating professional, production-ready thumbnails for articles or newsletters. It reads the article copy, proposes multiple composition concepts (e.g., bold claim, conceptual object), writes tailored prompts, calls the Gemini API for image generation, and evaluates the results using computer vision, returning ranked candidates with rationale.

Unified design skill covering brand identity, design tokens, UI styling, AI logo generation, corporate identity programs, HTML presentations, banners, icons, and social media photos. Automates logo design, CIP mockups, slide decks, and multi-platform social images.

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.

A comprehensive skill for generating multimodal media content using fal.ai models. It supports text-to-image (Nano Banana), text/image-to-video (Veo, Kling, Seedance), and text/video-to-audio (CSM-1B, ThinkSound). Use this tool for any creative project requiring high-quality generated images, videos, or sound effects.