Courses & Learning

Turn a repeated workflow into an Agent Skill, design its discovery and activation, write SKILL.md, bundle scripts, references, and assets, then evaluate, secure, and ship it.

How language models work, writing prompts and project rules, curating context, agents and tools, verifying AI output, and using AI safely.

Audit an entire codebase, a module, or recent changes with AI to find bad state management, boolean explosions, dead code, naming problems, and other code smells, then fix them.

Train a small language model with Language Model Builder on a Mac. Covers tokens and embeddings, designing the run, pre-training and reading loss, fine-tuning with SFT and DPO, and comparing checkpoints in a lab report.

Build a TypeScript MCP server with tools, resources, and prompts, move it to remote HTTP with authorization and security boundaries, then deploy and review it.

A beginner's introduction to Claude Code, covering the statusline, exploring a codebase, how Claude manages memory, its modes, and setting up permissions.

Claude Code's skill system, covering how to run and locate skills, write your own, use the skill marketplace, and chain skills like interview-me, new-tests, deepstack, and GitHub Actions into automated workflows.

Set up any project for AI-assisted development with a single command, write framework rules, and establish guardrails that keep AI output consistent and correct from the start.

Choose an open-weight model that fits your hardware, run it locally with Ollama and Node.js, build a private AI feature with structured output and fallbacks, and operate local AI responsibly.

What MCP solves, how hosts, clients, servers, tools, resources, and prompts fit together, and how to connect, configure, test, and troubleshoot an existing server you trust.

Principles and techniques for handing more work to an AI coding assistant, centered on context, prompt, and model rather than any one app. Covers prompting in production codebases, spec workflows, common pitfalls, and agentic loops.