Automate document processing by extracting text, tables, and structured data from forms, invoices, and receipts. Build Java applications that leverage Azure Document Intelligence prebuilt models or create custom document analyzers.

Manually processing invoices, receipts, and forms is slow and error-prone. This skill automates document analysis using Azure Document Intelligence to extract text, tables, and fields with high accuracy.

Process invoices, receipts, and documents automatically using Azure Document Intelligence SDK in .NET. Extract structured data, text, and tables from PDFs and images without manual data entry.

Transform unstructured media files into structured, searchable content for RAG applications and automated workflows. Use prebuilt analyzers or create custom field extraction models with the Azure AI Content Understanding SDK.

Detect anomalies in time-series data using Azure Cognitive Services. This skill provides Java SDK patterns for univariate and multivariate anomaly detection with real-time streaming support.

Converts audio recordings into searchable text and generates professional meeting notes with AI-powered summaries using Claude or GitHub Copilot integration.

Many teams track data that cannot be trusted for decisions. This skill designs measurement strategies that produce accurate, decision-ready analytics data.

This skill enables Claude to automate Amplitude product analytics workflows including event tracking, user activity lookup, cohort management, and user identification through Rube MCP.

This workflow bundle provides a comprehensive guide for building production AI applications, from LLM integration to RAG systems and AI agents. It orchestrates multiple specialized skills into a cohesive development process.

LLM agents often fail in production despite passing benchmarks. This skill provides behavioral testing, capability assessments, and reliability metrics to catch issues before deployment.

A/B tests often fail due to poor design, premature stopping, and invalid metrics. This skill enforces rigorous methodology with mandatory gates for hypothesis locking, metric definition, and sample size calculation before any test runs.

AI agents struggle to learn from past experiences and improve over time. ReasoningBank provides adaptive learning patterns using AgentDB so agents can track trajectories, judge outcomes, and distill memories into reusable patterns.

Traditional databases struggle with semantic search queries. AgentDB delivers 150x faster vector operations with sub-millisecond search times for building intelligent RAG systems and knowledge bases.

AgentDB vector searches slow down as data grows, causing application lag. This skill provides quantization and indexing techniques to achieve 150x faster searches with 4-32x memory reduction while maintaining accuracy.

Building self-learning agents requires complex reinforcement learning setup. This skill provides templates and guidance for 9 algorithms including Decision Transformer, Q-Learning, and Actor-Critic.

Build sophisticated distributed AI systems with sub-millisecond synchronization and advanced search capabilities. Learn to implement QUIC sync, custom distance metrics, and hybrid vector plus metadata search for production applications.

Measuring agent quality requires structured approaches. This skill provides multi-dimensional evaluation rubrics, test set management, and production monitoring to continuously assess and improve agent performance.

Limited context windows constrain complex tasks and increase API costs. This skill provides proven techniques to double or triple effective context capacity through compaction, observation masking, KV-cache optimization, and context partitioning.

Context is the foundation of effective AI agent performance. This skill teaches you how to understand, design, and optimize context in agent systems. Learn the principles of progressive disclosure, attention mechanics, and context budgeting to build more capable AI agents.

Manual evaluation of LLM outputs is slow and inconsistent across reviewers. This skill provides production-grade techniques for automated evaluation using LLMs as judges. It includes direct scoring rubrics, pairwise comparison with position bias mitigation, and confidence calibration.