Skill UI

This skill provides guidance on implementing common architectural patterns and best practices within the PyTorch framework. It is designed for developers building sophisticated deep learning models, helping to improve structure, efficiency, and code maintainability when working with neural networks.

Guides ML teams through reviewer-style ablation planning, covering context gathering, structured experiment design, feasibility checks, and compute-aware sequencing before implementation.

This skill guides the entire process of writing a research paper rebuttal following submission to a major conference. It parses complex, multi-reviewer feedback, structures responses according to strict venue rules (e.g., text-only, per-reviewer threads), and ensures all claims are grounded in the original paper, preventing fabrication or overpromising. It manages follow-up rounds and maintains academic rigor.

Provides an expert methodology to significantly reduce AI API spending (40-80%) without sacrificing user quality. The guide covers cost auditing, optimizing existing systems, and designing cost-efficient architectures using techniques like model routing, prompt caching, output length control, and prompt compression.

This skill provides a systematic, four-phase workflow for diagnosing and recovering from AI agent failures. It guides the agent to first capture the failure state, diagnose the root cause (e.g., loop, context overflow, state drift), apply minimal containment recovery actions, and finally generate a detailed introspection report, minimizing the need for human intervention.

Describes how to use the MemOS local memory toolkit to recall past conversations, search shared histories, and choose the right memory tool when automatic recall is insufficient.

This guide details the OpenViking long-term memory plugin, which enhances conversational AI by automatically capturing key facts and preferences from past interactions. It utilizes auto-capture modes (semantic or keyword) to store memories and automatically recalls relevant context before generating a response, ensuring continuity and personalization across long conversations. Provides tools for retrieval, manual storage, and memory deletion.

This skill guides the generation of a complete, production-ready Model Context Protocol (MCP) server using C# and .NET. It covers advanced architectural patterns, including Host builder setup, proper dependency injection, structured logging, and implementing robust functional tools. Ideal for developers building sophisticated AI agents or backend services that require standardized communication and tool invocation capabilities.

Provides patterns and techniques for building robust evaluation loops for AI agents. This skill guides the implementation of self-critique, evaluator-optimizer pipelines, and test-driven refinement workflows. Use it to significantly enhance the accuracy and quality of complex outputs like code, reports, and analyses by implementing structured, iterative improvement cycles (Generate → Evaluate → Critique → Refine).

Conducts comprehensive AI prompt safety reviews that analyze bias, misinformation, injection, and privacy risks while delivering effectiveness evaluations, security guidance, and best-practice recommendations for prompt engineers.

This skill guides users on setting up and running LLM-as-judge evaluations using Arize. It covers defining evaluators (including prompts, classification choices, and models) and executing tasks against real data spans or experiments. It supports key metrics like hallucination, faithfulness, and correctness, and facilitates continuous monitoring for comprehensive LLM performance analysis.

Interactive workflow that interrogates scope, deliverables, constraints, and success criteria while guiding users to refine task prompts; copies the final markdown with Joyride clipboard commands and never writes code.