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.

An AI skill for Claude, Codex, and Claude Code

This workflow guides you through building autonomous AI agents, from single-agent implementation to multi-agent systems with orchestration using CrewAI and LangGraph frameworks.

Deploy custom AI agents as containerized services in Azure AI Foundry without managing infrastructure. Use the Azure AI Projects SDK to define, deploy, and manage hosted agents with your own Docker images and integrated tools.

Multi-agent workflows often suffer from coordination bottlenecks and unmanaged costs. This skill provides profiling, orchestration strategies, and cost controls to maximize efficiency.

Poorly designed tool schemas cause agents to hallucinate, fail silently, or waste tokens. This skill teaches proven patterns for clear, unambiguous function-calling interfaces that work reliably.

This skill helps developers systematically improve AI agent performance through data-driven analysis, prompt engineering, and structured testing workflows, enabling continuous agent optimization with measurable results.

Build intelligent memory architectures for AI agents that enable long-term learning and context-aware responses. This skill provides patterns for implementing short-term, long-term, and episodic memory that improves agent performance over time.

This skill provides AI agents with persistent, searchable memory to retain architecture decisions, patterns, and knowledge across sessions without manual tracking.

This skill enables Claude to manage multiple local CLI agents running in parallel tmux sessions, providing start/stop/monitor capabilities and cron-friendly scheduling for automated workflows.

Create persistent AI agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK. This skill provides code examples for building agents with hosted tools, function tools, and conversation threads.

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

This skill helps developers systematically address PR review comments using the GitHub CLI, ensuring no feedback is missed and all issues are properly resolved.

Security teams need comprehensive reference material for authorized Active Directory assessments. This skill provides documented attack techniques and tool commands for penetration testers conducting red team operations.

Marketing teams and sales professionals waste hours on repetitive ActiveCampaign tasks like contact management and automation enrollment. This skill enables AI assistants to execute these workflows automatically through the Rube MCP integration.

This skill helps developers conduct comprehensive WCAG compliance audits using automated tools and manual testing to identify accessibility barriers and provide remediation guidance.

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.

Build stunning 3D websites and web apps using Three.js, React Three Fiber, and Spline. This skill helps you create interactive product configurators, immersive portfolios, and engaging 3D interfaces that work across all devices.

Developers struggle to maintain consistent, accessible UI components across React projects. This skill provides CLI commands, component composition patterns, and styling rules for building professional UIs with the shadcn/ui component library.

Claude users struggle to organize their Obsidian notes consistently. This skill provides automated PARA classification, routing, and vault hygiene reviews to keep knowledge bases organized without manual effort.