A practitioner-led course on Claude, Cowork, Skills, MCP and subagents — for engineers and operators who would rather ship than scroll.
Cover · Haythem RehoumaThe artifacts you walk away with — not slides, real things you can run, fork and ship the day you finish the masterclass.
CLAUDE.mdMost AI courses sell you slides. This one hands you a toolkit you'll still be using six months later — Skills you wrote, a CLAUDE.md you'll defend, a pipeline you'll trust.— Haythem Rehouma, Senior Practitioner
Three principles that separate a working masterclass from a content farm. Every module reflects them — no exceptions.
XML structure, Constitutional AI, Cowork briefs, MCP, Skills frontmatter — covered in depth, not as side notes after a generic GPT chapter.
Each module ends with a real artifact: a Skill, a CLAUDE.md, a subagent pipeline, an MCP integration. Theory only where theory pays.
The capstone is a real project with deliverables. Your certificate is verifiable and the workflow stays useful long after.
A free, open catalogue of 1,441 reusable Claude skills across 71 categories — installable in Claude Code, Cursor, Codex CLI and Gemini CLI.
Search 1,441 skills…/Use before creative or constructive work (features, architecture, behavior). Transforms vague ideas into validated designs through disciplined reasoning and collaboration.
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks.
You are a frontend designer-engineer, not a layout generator.
Transform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical approaches.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers and stand the test of time.
Terraform infrastructure as code best practices
Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)
Three days free, no card required. Cancel any time. Pricing is per learner; team plans on request.
3 days, full access to Module 01.
Everything you need to use Claude daily.
Full mastery — Claude Code, Skills, Subagents, MCP.
Field notes
Hands-on field guides on Claude Code, RAG, AI architecture and the workflows of AI-augmented developers.
Where this is going in 2026 and beyond. What I'd bet on, what I would not, and the line where I get sceptical of the hype.
Read →Once you've outgrown the defaults: hooks for deterministic side effects, MCP servers for org-specific data, custom tools, and system-prompt surgery.
Read →How engineering teams are actually integrating Claude Code today. The shared .claude/ folder, the review rituals, and the anti-patterns I keep seeing in the wild.
Read →Letting Claude Code own the entire test loop. Including the parts that make engineers nervous: regressions, flakies, integration tests, and the stack-trace whisperer.
Read →
I'm Haythem Rehouma. I've spent the last decade shipping software, teaching engineers, and burning hours inside Anthropic's stack so you don't have to. This masterclass is what I wish I'd had on day one.
I won't pretend Claude is magic. I'll show you exactly where it earns its keep — and where it'll waste your afternoon. Every artifact you build here, I've shipped to production at least once.
Three days free, no card required. Keep your Skills, your CLAUDE.md and your habits — forever.