Skill UI

This expert analyzes and refactors provided code based on clean code principles, SOLID design patterns, and modern software engineering best practices. It is designed to significantly improve the quality, maintainability, and performance of complex, messy, or poorly structured codebases, ensuring the resulting code is robust, scalable, and easy to maintain.

This expert analyzes and refactors existing codebases to enhance quality, maintainability, and performance. It specializes in applying clean code principles, SOLID design patterns, and modern software engineering best practices. Use it to clean up technical debt, simplify complex modules, or prepare a codebase for new feature development.

A comprehensive, phased guide detailing how to migrate your code review process to CodeRabbit. It covers the entire journey, from assessing current tools (like SonarCloud, DeepSource, or manual reviews) and mapping existing rules, through to running a parallel pilot phase and finally achieving full adoption. Ideal for engineering managers or DevOps teams planning a major CI/CD tool transition.

Guides chaos engineering experiments by defining objectives, choosing tools such as Chaos Mesh, Gremlin, Toxiproxy, or AWS FIS, injecting failures, monitoring metrics, and recommending fixes to harden services and APIs.

This skill analyzes the predictable ways language models lose performance as context length increases. It details core patterns, including 'lost-in-middle,' context poisoning, and distraction. Use this knowledge to diagnose unpredictable agent failures, design highly reliable systems for long document processing, and implement advanced context engineering strategies.

A comprehensive guide to understanding the complete state (context) available to Large Language Models during inference. Covers core components like System Prompts, Tool Definitions, Message History, and Retrieval Augmented Generation (RAG). Learning to engineer context is crucial for building robust, efficient, and reliable AI agent systems by managing the attention budget and ensuring high-signal information delivery.

Provides CTO-level frameworks for technology strategy, tech debt assessment, architecture governance, engineering team scaling, vendor evaluation, and crisis management.

This skill provides advanced engineering patterns to dramatically improve the performance and reliability of Customer.io API integrations. It implements critical optimizations such as HTTP connection pooling, LRU deduplication caching, parallel batch processing, and fire-and-forget async tracking. Use this when integrating Customer.io into high-throughput, mission-critical systems to reduce latency from seconds to milliseconds.

Guides data engineering patterns for ETL pipelines, Spark analytics, and quality checks, showcasing Python and SQL snippets to extract, transform, load, validate, and model sales data in modern warehouses.

A comprehensive, end-to-end workflow for building product features guided by rigorous data insights. This skill guides users through the entire lifecycle, encompassing exploratory data analysis, forming measurable business hypotheses, designing statistical A/B tests, architecting data pipelines, and implementing robust backend/frontend instrumentation. It ensures that every feature iteration is validated by data and measured for impact.

An expert in designing, implementing, and optimizing scalable, reliable, and cost-effective data pipelines for both batch and streaming data. Covers advanced topics including ETL/ELT patterns, Kappa/Lambda architectures, workflow orchestration (Airflow/Prefect), transformation using dbt/Spark, and managing modern storage formats like Delta Lake and Iceberg. Focuses heavily on data quality, monitoring, and cost optimization strategies.

This guide outlines the complete MLOps workflow on Databricks. It covers feature engineering using Feature Store, tracking experiments with MLflow, managing model versions in the Model Registry, and deploying real-time inference endpoints via Mosaic AI Model Serving. Ideal for building robust, production-grade ML pipelines.