Skill UI

Designs and implements production-grade RAG systems with document chunking, embeddings, vector stores, hybrid search, reranking, and evaluation, ideal for knowledge-grounded AI apps that need semantic retrieval, similarity search, and context augmentation.

Expert in designing and implementing advanced Retrieval-Augmented Generation (RAG) pipelines. This role focuses on optimizing the entire information retrieval process—from document chunking and embedding model selection to vector database architectures and hybrid search strategies. The goal is to bridge the gap between raw knowledge documents and accurate LLM understanding, drastically reducing hallucination and enhancing context relevance for enterprise applications.

This comprehensive workflow guides the end-to-end implementation of Retrieval-Augmented Generation (RAG) systems. It covers critical stages, including selecting optimal embedding models, setting up vector databases, designing chunking strategies, implementing hybrid retrieval, integrating Large Language Models (LLMs), and performing rigorous evaluation. Use this when building knowledge-grounded AI applications or advanced semantic search systems.

Automate Raisely workflows via Composio's Rube MCP connector, ensuring you search tools first, manage active connections, and invoke RUBE_MULTI_EXECUTE_TOOL with schema-compliant arguments for reliable execution.

Ray Data offers scalable distributed data processing for ML workloads, streaming across CPU/GPU clusters and integrating with PyTorch, TensorFlow, and Ray Train. Use it for batch inference, ETL, and multi-modal preprocessing from a laptop up to hundreds of nodes.

Ray Train orchestrates distributed PyTorch, TensorFlow, and HuggingFace workloads from laptops to clusters, automating GPU placement, fault tolerance, checkpointing, and hyperparameter sweeps so teams can scale massive model training with minimal code changes.

A comprehensive optimization guide maintained by Vercel, covering 45 rules for React and Next.js. Use this resource when building new components, implementing complex data fetching (client or server-side), refactoring code, or systematically improving bundle size and overall load times for high-performance web applications.

Automated assistance for building React components, offering best practices, production-ready code generation, and validation guidance for frontend patterns like accessibility and performance optimization.

This guide outlines best practices for building highly flexible and maintainable React components. It addresses common architectural pitfalls, such as 'boolean prop proliferation,' by recommending advanced patterns like compound components, state lifting, and context providers. Use this when refactoring large component libraries, designing robust APIs, or reviewing component architecture, including considerations for React 19 APIs.

A comprehensive architectural guide for building production-grade flowcharts using ReactFlow. This pattern set covers key challenges including hierarchical tree navigation (expandable/collapsible nodes), performance optimization via incremental rendering and memoization, and advanced state management using Redux-like reducer patterns with history tracking (undo/redo).

This skill provides comprehensive patterns and templates for developing custom, reusable node components within the React Flow library. It ensures adherence to best practices by integrating proper TypeScript types and facilitating connection with global application state stores. Ideal for building complex, interactive workflow diagrams and visual programming interfaces.

Automates React hook creation support by guiding on best practices, providing production-ready code/configuration, and validating outputs for modern frontend scenarios.