Skill UI

Creates new Feishu Cloud Docs from Lark-flavored Markdown, letting you optionally target folders, wiki nodes, or knowledge spaces while ensuring structured, rich, and visually varied content.

This skill enables the generation of high-quality, cinematic videos using a highly structured prompt format (JSON). Users define detailed cinematic elements—including background, characters, camera movements, dialogue, and audio—and can optionally provide a reference image to guide the visual style or content of the final output. It automates the complex AIGC video generation workflow.

A comprehensive skill for creating technical and scientific documentation using Markdown as the source format, enhanced by embedded Mermaid diagrams. This method establishes text-based diagrams as the canonical standard, ensuring that all visualizations are clean, editable, and highly readable in version control systems like Git. It is ideal for generating reports, architectural diagrams, workflows, and any content that requires cross-platform rendering and version history.

MarkItDown is a lightweight utility designed to convert heterogeneous documents (PDF, Office files, HTML, etc.) into structured, plain Markdown. It is specifically optimized for text analysis, search indexing, and preparing data for Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) systems, prioritizing content structure over visual fidelity. Supports local, stream, and advanced multimodal extraction scenarios.

This skill restructures AI-generated content to maximize cognitive accessibility, specifically optimized for users with ADHD or neurodivergence. It uses evidence-based techniques such as chunking, visual hierarchy, front-loading key points, and progressive disclosure. It offers three distinct modes (clean, flow, zen) to tailor the output structure, ensuring that complex information is highly digestible and easy to follow.

Programmatically manages advanced elements on Miro boards using the REST API v2. Functions include creating connectors, uploading images (from URL or Base64), embedding external content (like videos/URLs), managing custom App Cards, and adding documents. Ideal for building complex, automated, and visually rich workflows, architecture diagrams, and collaborative dashboards.

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.

This skill functions as a dedicated prompt engineer, transforming vague ideas or initial drafts into highly optimized, production-ready prompts. It adapts its methodology based on the target AI model (e.g., Claude, GPT, Midjourney), ensuring the best practices, structure, and constraints are applied for maximum output quality and token efficiency. Ideal for complex content generation, coding tasks, and creative visual prompts.

This skill provides the comprehensive reference architecture and implementation patterns for integrating Runway's advanced AI capabilities. It focuses on guiding developers through the process of AI video generation, image-to-video conversion, and creative content creation using the dedicated Python SDK. Use this when building applications that require high-quality, generative visual media.

This technique guides users on how to use visual descriptions from music videos (MV), such as specific scenes, emotional themes (grief, loss), or real-world events, as powerful search anchors. Instead of only searching by title or artist, users can extract keywords from the visual narrative to refine search queries, significantly increasing the chances of identifying the correct song or tracing its origin. Ideal for music research and cultural analysis.

Generate a cohesive three-panel social media carousel (1080x1080), designed for cinematic storytelling. Perfect for creating multi-part, on-brand content series for platforms like Instagram, LinkedIn, or X. The skill ensures the panels read as one continuous narrative while maintaining individual visual appeal.

A skill designed to generate cinematic, short-form video clips (3-10 seconds) suitable for marketing reveals, product teasers, or ambient loops. It focuses on generating one cohesive shot per request, ensuring high quality and narrative focus for modern video models like Seedance, Kling, and Veo. Ideal for creating impactful, bite-sized visual content.