Explore our collection of Agent Skills to enhance your AI workflow.
Manages Proxmox VE environments including virtual machines, LXC containers, and cluster configurations with integrated automation patterns.
Conducts automated accessibility audits to ensure web applications comply with WCAG standards and ARIA best practices.
Generates comprehensive character designs, animation states, and code-ready motion specifications for AI mascots and avatars.
Generates and edits professional draw.io diagrams in XML format for technical architecture and flowcharts.
Automates the assembly of professional RFP responses using a reusable library of capability blocks, case studies, and team biographies.
Manages Things 3 tasks, projects, and areas directly within Claude Code using the things3-cli on macOS.
Automates the creation and configuration of high-quality GitHub Projects with standardized descriptions, READMEs, and linked repositories.
Analyzes videos and screen recordings by extracting frames and transcripts for deep visual comprehension.
Searches Twitter/X in real-time using the Grok API to track trends, monitor accounts, and analyze social discussions.
Implements and guides GitOps best practices for cloud-native infrastructure and Kubernetes application delivery.
Automates high-quality AI image generation via Google Gemini with advanced style matching and browser-based automation.
Programmatically creates, edits, and refines professional Excalidraw diagrams with real-time canvas synchronization and visual feedback.
Streamlines the creation, testing, and deployment of Massdriver infrastructure bundles with integrated compliance and upgrade validation.
Captures high-quality screenshots of specific application windows or fullscreens automatically based on conversation context.
Lists active macOS windows with application names and IDs to streamline screen capture workflows.
Builds and manages custom Claude Code extensions, including skills, hooks, plugins, and slash commands through specialized builder agents.
Implements comprehensive audio processing and text-to-speech generation using the Google Gemini API.
Generates high-quality, narrative-driven image prompts for Gemini Imagen via the Nanobanana MCP.
Captures and structures professional accomplishments, lessons, and insights directly from your development workflow.
Streamlines Tailwind CSS v4 development with expert guidance on CSS-first configuration, modern directives, and version migration.
Edits Remotion video projects by managing JSON configurations and TSX source code for programmatic video creation.
Processes, converts, and optimizes audio and video files using FFmpeg through guided AI interactions.
Analyzes and extracts insights from images, videos, and audio files using advanced AI models.
Preserves and retrieves historical context, error records, and code references to prevent information loss during Claude Code session compactions.
Generates professional AI videos from text or images using state-of-the-art models like Sora, Veo, and Kling.
Transforms raw datasets into professional-grade charts, graphs, and visual plots using intelligent data analysis.
Implements mobile-first design principles, platform-specific conventions, and high-performance patterns for iOS and Android applications.
Bootstraps and configures dynamic frontend plugins for Red Hat Developer Hub, including UI components, entity cards, and custom themes.
Automates API testing workflows using Newman and Postman collections with robust environment management and reporting.
Transcribes audio files locally using whisper.cpp with CUDA acceleration for high-performance speech-to-text conversion.
Scroll for more results...