timothywarner-org

Develop and extend the WARNERCO Robotics Schematica system - an agentic RAG application with FastAPI, FastMCP, LangGraph orchestration, and 3-tier memory (JSON/Chroma/Azure AI Search). Use when working on the schematica backend, adding schematics, modifying the LangGraph flow, updating dashboards, or deploying to Azure.

Build Model Context Protocol (MCP) servers in Python (FastMCP), JavaScript, or TypeScript. Use when creating new MCP servers, adding tools/resources/prompts, configuring transports (stdio/HTTP), or debugging MCP protocol issues. Triggers on requests for MCP development, AI tool creation, or Claude Desktop integration.

Expert Azure Principal Architect providing guidance using Azure Well-Architected Framework (WAF) principles and Microsoft best practices. Use for cloud architecture decisions, Azure service selection, infrastructure design, and WAF pillar assessments.

Expert assistant for developing Model Context Protocol (MCP) servers in Python using FastMCP, mcp package, Pydantic, and async patterns. Use when building MCP tools, resources, prompts, or debugging Python MCP server issues.

Audit the CLAUDE.md hierarchy in a repo for drift between what each CLAUDE.md claims and what's actually on disk. Validates that referenced file paths still exist, flags voice violations (em dashes, "ask" as a noun), and checks the ground-truth facts block for stale tokens (MCP spec date, transports, model lineup). Use when the user asks to audit, validate, check, or verify CLAUDE.md files, says "is my CLAUDE.md still accurate", flags possible doc drift, or wants to sanity-check the docs before a course recording or release.

Review uncommitted local changes in the current git working tree for bugs, smells, missing tests, and CLAUDE.md voice violations. Use when the user asks to "review my changes", "look at my diff", "check my staged changes", "code review my working tree", or wants a sanity check before committing or opening a PR. Do NOT use for already-open pull requests on GitHub (that's the separate `review` command).

Scaffold production-ready Python MCP servers using FastMCP. Use when creating new MCP servers, initializing MCP projects, generating server boilerplate, or setting up MCP development environments. Supports all MCP primitives (tools, resources, prompts) with Pydantic validation, async patterns, and proper project structure.

Generate GH-300 practice questions that feel like the real exam without copying it. Every item is grounded in current Microsoft Learn content, uses modern Copilot terminology, and follows Microsoft-style exam item rules (scenario-first, plausible distractors, no trick wording). Use when the user asks for practice questions, quiz items, or exam prep.

Create short GH-300 practice exercises (10-20 minutes) that are executable and self-validating. Every exercise includes prerequisites, exact tasks, validation steps, expected outcomes, and rollback. Use when the user asks for a hands-on exercise, practice flow, or guided walkthrough.

Generates a personalized GH-300 study plan based on the user's self-assessed confidence across exam skill areas, prioritizing weak areas with estimated hours and Microsoft Learn links. Use when the user asks for a study plan, is unsure what to study, or wants exam prep guidance.

Generate AB-100 practice questions that feel like the real exam without copying it. Every item is grounded in current Microsoft Learn content, uses modern Microsoft product names (Microsoft Foundry, Copilot Studio, Microsoft Entra ID), and follows the Microsoft Worldwide Learning Exam Writing Style Guide (WWL). Use when the user asks for practice questions, quiz items, or exam prep.

Create short AB-100 practice labs (15-25 minutes) that are executable and self-validating. Every lab includes prerequisites, exact tasks, validation steps, expected outputs, and cleanup. Scope covers agent design walkthroughs, Copilot Studio authoring, Microsoft Foundry tool configuration, ALM patterns, and governance controls. Use when the user asks for a hands-on lab, practice exercise, or guided walkthrough.

Generates a personalized AB-100 study plan based on the user's self-assessed confidence across the three AB-100 domains, prioritizing weak areas with estimated hours and Microsoft Learn module links. Use when the user asks for a study plan, is unsure what to study, or wants exam prep guidance.

Generate AZ-104 practice questions that feel like the real exam without copying it. Every item is grounded in current Microsoft Learn content, uses modern Azure terminology, and follows Microsoft-style exam item rules (scenario-first, plausible distractors, no trick wording). Use when the user asks for practice questions, quiz items, or exam prep.

Create short AZ-104 practice labs (10-20 minutes) that are executable and self-validating. Every lab includes prerequisites, exact tasks, validation steps, expected outputs, and cleanup. Use when the user asks for a hands-on lab, practice exercise, or guided walkthrough.

Generates a personalized AZ-104 study plan based on the user's self-assessed confidence across exam skill areas, prioritizing weak areas with estimated hours and Microsoft Learn module links. Use when the user asks for a study plan, is unsure what to study, or wants exam prep guidance.

Generate AB-900 practice questions that feel like the real exam without copying it. Every item is grounded in current Microsoft Learn content, uses modern M365 and Purview terminology, and follows Microsoft-style exam item rules (scenario-first, plausible distractors, no trick wording).

Generate realistic 5-10 minute admin scenario walkthroughs through M365 admin centers. Each walkthrough is a guided simulation of a real AB-900 admin task with numbered steps, exact navigation paths, correct settings, and exam relevance notes.

Generates a personalized AB-900 study plan based on the user's self-assessed confidence across the three exam domains, prioritizing weak domains with estimated hours and Microsoft Learn module links.

Create guided hands-on CKA practice labs (15-30 minutes) that run on kind clusters. Every lab includes prerequisites, step-by-step instructions with explanations, validation gates, troubleshooting tips, and cleanup. Use when the user asks for a hands-on lab, guided exercise, or learning walkthrough.

Generate CKA exam-realistic practical scenarios that match the format, difficulty, and style of real CKA performance-based tasks. Each scenario presents a task the candidate must complete using kubectl commands against a Kubernetes cluster. Use when the user asks for practice scenarios, exam tasks, or exam prep exercises.

Generates a personalized CKA study plan based on the user's self-assessed confidence across the five exam domains, prioritizing weak areas with estimated hours and Kubernetes documentation links. Use when the user asks for a study plan, is unsure what to study, or wants exam prep guidance.

Generate AI-901 practice questions that feel like the real Microsoft Azure AI Fundamentals exam without copying it. Every item is grounded in current Microsoft Learn content, uses modern Microsoft product names (Microsoft Foundry, Azure AI Language, Azure AI Speech, Azure AI Vision, Azure Content Understanding), and follows the Microsoft Worldwide Learning Exam Writing Style Guide (WWL). Use when the user asks for practice questions, quiz items, or exam prep.

Create short AI-901 practice labs (15-25 minutes) that are executable and self-validating. Every lab includes prerequisites, exact tasks, validation steps, expected outputs, and cleanup. Scope covers Microsoft Foundry portal builds, Foundry Python SDK client apps with keyless authentication, Azure AI Services via Foundry Tools, and Azure Content Understanding analyzers. Use when the user asks for a hands-on lab, practice exercise, or guided walkthrough.

Generates a personalized AI-901 study plan based on the learner's self-assessed confidence across the two AI-901 domains and their sub-areas, prioritizing weak areas with estimated hours, Microsoft Learn module links, and the matching Microsoft Press video lesson. Use when the learner asks for a study plan, is unsure what to study, or wants exam prep guidance for Microsoft Azure AI Fundamentals.

Runs the project linter and reports style issues. Used after code changes to ensure consistency.

Checks deployment readiness by verifying build status and test results before proceeding.

Runs project linting and reports issues. Used after code changes to ensure style compliance.

Pipeline review and architectural validation skill for the Contoso HR Agent project. Covers LangGraph + CrewAI + FastMCP 2 + Pydantic v2 patterns and the rules specific to this codebase. Use when reviewing any change to src/contoso_hr/ or when adding new pipeline components.

Expert skill for teaching LangGraph - the orchestration framework for stateful AI agents. Covers StateGraph, nodes, edges, conditional routing, checkpointing, human-in-the-loop, and multi-agent patterns. Invoke when users ask about LangGraph, building agent graphs, state machines for LLMs, or workflow orchestration. Keywords: langgraph, state graph, agent workflow, orchestration, multi-agent, checkpointing, human-in-the-loop.

Reference knowledge for the OWASP Top 10 (2021) web application security risks. Use when scanning code for vulnerabilities, reviewing security posture, classifying findings by severity, or providing remediation guidance aligned with OWASP standards.