Analytics & Monitoring Agent Skills for OpenAI Agents SDK

Use when designing an A/B or split test: define the hypothesis, control and variants, estimate sample size, verify tracking, and…

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate…

Expert in designing and building autonomous AI agents.

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent…

Azure AI Text Analytics SDK for sentiment analysis, entity recognition, key phrases, language detection, PII, and healthcare NLP.

Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping.

Build image analysis applications with Azure AI Vision SDK for Java.

Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication.

Build document analysis applications using the Azure AI Document Intelligence SDK for Java.

Extract text, tables, and structured data from documents using prebuilt and custom models.

Build interactive React dashboards in Treasure Work using render_react.

Use this skill when asked to read an arxiv paper given an arxiv URL

Implement Real User Monitoring (RUM) to capture actual user performance

Execute this skill empowers AI assistant to construct recommendation

Use when designing or auditing ACM RecSys experiments centered on offline-versus-online evaluation — temporal splits, equal-budget…

Use when positioning an ACM RecSys submission against recommender-systems literature and its neighbors (SIGIR, KDD, WSDM, TheWebConf…

Use when strengthening the reproducibility of an ACM RecSys paper or preparing a RecSys Reproducibility Track submission — pinning dataset…

Analyze authorized videos into original prompt contracts.

Automatically invoke this skill whenever the user asks to refresh a semantic model or a dataset.

Analyzes rehabilitation data to track recovery progress, identify physical patterns, and optimize recovery training plans.

When to activate: reinforcement learning, RL, Gymnasium, Stable-Baselines3, PPO, DQN, SAC, reward shaping, agent training