Skill UI

Cross-database SQL performance optimization assistant offering query tuning, indexing strategies, pagination, batch operations, and monitoring guidance for MySQL, PostgreSQL, SQL Server, Oracle, and other relational systems.

A comprehensive coaching guide for advancing careers in the technology industry, covering roles like Software Engineering, Data Science, and Product Management. It provides actionable strategies for resume optimization (ATS format), technical interview preparation (Algorithms, System Design, Behavioral), salary negotiation, and navigating complex career paths (IC vs. Management). It adapts advice to both global (FAANG) and Chinese tech ecosystems.

Accelerate scientific Python code on NVIDIA hardware using CUDA and RAPIDS libraries. Optimizes NumPy, pandas, scikit-learn, and ML workloads for GPU execution. Includes profiling, memory management, and kernel optimization to ensure correctness and performance gains.

High-performance Python DataFrame library built on Apache Arrow. Covers expression-based API, lazy query optimization, streaming out-of-core processing, aggregations, window functions, joins, and pandas migration for ETL and analytics pipelines.

This advanced skill optimizes LLM context usage by implementing strict rules for prompt caching, efficient log pruning, AST-based code inspection, and compact data structuring. It minimizes token consumption and maximizes information density, suitable for highly technical and iterative development workflows.

A comprehensive guide to diagnosing and fixing performance bottlenecks when using Qdrant. Covers optimizing slow uploads, resolving stuck optimizers, and tuning HNSW parameters, including best practices for sharding, bulk loading, and multi-tenant indexing to ensure efficient vector search performance.

A comprehensive guide for developers to optimize performance when integrating Adobe APIs (Firefly, PDF, Photoshop). Techniques covered include implementing token caching, parallelizing asynchronous job submissions, leveraging response caching (LRU), and optimizing connection handling to minimize latency and maximize throughput.

This guide outlines advanced strategies to optimize latency and throughput when integrating Anthropic's Claude API. Learn critical techniques such as streaming responses, prompt caching, model selection (Haiku, Sonnet, Opus), and request parallelization, ensuring your applications provide a low-latency, high-performance user experience.

This guide provides advanced techniques to boost Framer API performance. It covers critical optimization areas including batch CMS syncing to prevent timeouts, memoizing expensive React components for better render performance, establishing persistent WebSocket connections, and optimizing image URLs before CMS synchronization. Use this when aiming to improve overall speed and stability of Framer-integrated applications.

This guide provides techniques to significantly boost performance when integrating with the Hex API. It covers essential optimization strategies such as implementing LRU caching for project lists, running multiple independent jobs in parallel, and adopting adaptive polling intervals to manage API latency and resource usage effectively. Use this when facing slow data retrieval or requiring high-throughput data processing.

A comprehensive guide to connecting any Kubernetes cluster (EKS, GKE, AKS) to CAST AI for cost optimization, autoscaling, and security monitoring. This skill covers the entire setup process, including generating API keys, installing the CAST AI agent via Helm charts, and integrating the provider using Terraform.

This guide sets up a robust local development loop for integrated Kubernetes infrastructure using CAST AI. It allows developers to test autoscaler policies, validate Terraform modules, and measure potential cloud cost savings in a dev environment before deploying to production. This is essential for building cost-aware and efficient CI/CD pipelines.