Skill UI

Conduct authorized security assessments for LLM applications and AI agents. Covers prompt injection, tool abuse, RAG exposure, memory poisoning, and system prompt extraction following OWASP LLM/ASI Top 10 guidelines. Includes red-teaming, vulnerability mapping, and compliance engineering for AI systems to ensure safety and robustness.

Design and implement complete machine learning pipelines using multi-agent orchestration following modern MLOps best practices. Covers data engineering, feature stores, model training, and production deployment. Ideal for building scalable, monitored, and reproducible ML systems in production environments.

Provides cross-language patterns for developing memory-safe systems code. This skill covers crucial concepts like RAII, ownership models, smart pointers, and robust resource management. It is essential for preventing common vulnerabilities such as use-after-free, memory leaks, and ensuring reliable resource handling across complex systems.

This skill provides methodologies for designing sophisticated, layered memory architectures for AI agents. It moves beyond simple context windows and basic vector stores by incorporating short-term, long-term, and graph-based memory systems. Implementing this is crucial for agents that require persistence across sessions, maintaining complex entity consistency, and performing advanced, relationship-driven reasoning over accumulated knowledge bases, including time-aware fact tracking.

This skill provides a comprehensive framework for mastering microservices architecture patterns. It covers critical aspects of building robust, distributed systems, including defining service boundaries (Domain-Driven Design), managing inter-service communication, handling distributed data transactions, and implementing various resilience patterns (e.g., circuit breaker, circuit breaker). It is essential for large-scale system decomposition.

Expert in building production machine learning systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Covers model serving, feature engineering, training optimization, MLOps, monitoring, and deployment in production environments.

Expert MLOps engineer specializing in building scalable ML infrastructure and automation pipelines. Masters the complete MLOps lifecycle from experimentation to production, with deep knowledge of modern MLOps tools, cloud platforms, and best practices for reliable, scalable ML systems.

MONOPOLY acts as a senior system design engineer to architect, review, and scale resilient backend systems. It guides on databases, microservices, caching, scaling, and infrastructure design, with design, review, scale, interview, and explain modes.

This skill specializes in designing and managing monorepo architectures for large-scale software development. It covers build systems like Nx, Turborepo, Bazel, and Lerna to optimize multi-project workflows. Use it for setting up new repositories, migrating from polyrepos, optimizing CI/CD pipelines, and managing dependencies across multiple applications efficiently.

This skill helps developers create custom external web service APIs for Moodle LMS. It covers following Moodle's API framework and coding standards, enabling integration with external applications, mobile backends, and course management systems using PHP.

Design and optimize production-grade multi-agent systems using LangGraph, LangChain, and DeepAgents. Provides structured workflows for creating supervisor, planner, researcher, coder, and validator agents with memory and tool-calling pipelines.

This skill covers designing multi-agent systems to overcome single-agent context limits. It includes patterns like supervisor/orchestrator, swarm, and hierarchical structures. Key concepts involve context isolation, parallel execution, token economics, and specialization for complex tasks.