Skill UI

This comprehensive guide details the architecture of memory for intelligent agents. It covers the distinction between short-term context, long-term vector storage, and advanced cognitive models (CoALA framework: semantic, episodic, procedural). Learn how to implement robust memory retrieval mechanisms, select appropriate vector databases (Pinecone, Qdrant, etc.), and utilize embedding models to build truly context-aware, persistent AI applications.

Prepares Claude with an ultra-granular, line-by-line code-analysis mode that maps invariants, assumptions, and flows before any vulnerability hunting, keeping context stable and reducing hallucinations during audits.

Prepares Claude with an ultra-granular, line-by-line code-analysis mode that maps invariants, assumptions, and flows before any vulnerability hunting, keeping context stable and reducing hallucinations during audits.

Identifies predictable context degradation patterns in large language models to diagnose failures and design resilient agents; covers lost-in-middle, poisoning, distraction, and confusion with mitigation tactics for long or complex conversations.

Explains what makes up a language model’s context state and how engineers should structure prompts, tools, retrieval, history, and outputs to guide agent behavior and manage token budgets.

Guides how to stretch limited LLM context windows by compressing, masking, caching, and partitioning information so agents process longer conversations or documents without enlarging models; includes when to trigger optimizations and concrete patterns for summaries, masking, KV-cache reuse, and budget tracking.

A comprehensive framework for building persistent memory systems within Large Language Models (LLMs). It supports multi-faceted memory management, including short-term context storage, long-term knowledge retrieval, and entity-based fact updates. This skill is crucial for developing sophisticated AI assistants that maintain coherence, recall user history over extended periods, and provide context-aware interactions by managing memory consolidation and retrieval relevance.

Cursor AI Debug Toolkit helps identify root causes of incorrect Cursor AI suggestions, inspect completion/chat context, and use dev tools/logs to tweak settings, re-test models, and document fixes for future issues.

This skill guides the architectural definition of complex business domains using Domain-Driven Design (DDD). It helps in defining core subdomains, separating services by bounded contexts, and establishing a unified ubiquitous language. It is essential for decomposing monoliths, structuring microservices, and aligning team ownership with clear domain boundaries.

This skill guides the planning and execution of complex business domains using Domain-Driven Design (DDD) principles. It helps developers move from strategic modeling (defining subdomains and bounded contexts) to tactical implementation patterns like CQRS, Event Sourcing, and Saga orchestration. Use it when dealing with complex, high-variability business rules and needing explicit architectural boundaries.

Frontend Patterns documents modern React and Next.js UI best practices, covering component composition, compound components, render-props, reusable hooks, and context-reducer state management to build performant interfaces.

Provides a senior migration architect workflow that researches legacy codebases, maps bounded contexts, and writes Strangler Fig-based modernization roadmaps so other teams can incrementally reshape systems.