learnclaude .dev

·  Courses    learnclaude.dev

Work that
earns the role.

Each track pairs a professional domain with a library of Claude Code skills you build, test, and keep. The DevOps / Cloud Platform track is live. More in development.

Browse courses The Cloud-Ready track

The Tracks

Curated for engineers moving into their next role.

  1. 01

    Getting Started with Claude Code

    Learn the fundamentals of Claude Code — installation, basic commands, and your first AI-assisted coding session.

    3 lessons 30 min Free
    Enter
  2. 02

    Kubernetes Operators, Incident Response & AI

    Build a Kubernetes operator with Claude Code — then use it to manage an AI workload, embed AI inside the reconciler itself, and wire it into an incident-response flow so the operator is both the managed system and a first responder. The takeaway is what the combination of operator + AI + Claude Code unlocks, not a generic Kubernetes tutorial.

    3 lessons 45 min Free
    Enter
  3. 03

    DevOps / Cloud Platform ready

    An outcome-driven track for working engineers moving into a DevOps or Cloud Platform role — but with a specific modern angle: you don't just learn the domain, you learn it through Claude Code and leave with a library of seven reusable Claude skills you built and validated yourself. Seven modules, each ending in a hands-on task you drive through Claude on your own laptop. The payoff is cutting time-to-response and time-to-action when it matters: when a page comes in, you're reaching for a skill you already built and validated, not starting from a blank terminal. No theory you don't immediately apply, and no copy-pasting without reading.

    28 lessons 560 min £150 · paid
    Enter

The Method

The loop every track closes.

You don't leave with tutorial notes. You leave with a folder of Claude Code skills you built, refined, and validated — ready to load on any future project.

  1. 01

    Work the problem through Claude, staying close to it.

    You drive. Claude assists. You read every file it produces before you run anything, and you ask for an explanation of anything opaque. AI acceleration is never a licence to disengage.

  2. 02

    Codify what worked as a reusable skill.

    Ask Claude to convert the session into a SKILL.md — a portable, re-loadable description of the task you just solved. Read it in full. If any step is opaque, it isn't ready.

  3. 03

    Validate in a fresh context — happy path and adversarial.

    Open a new Claude session with no history. Feed it a valid input; confirm the skill solves it unassisted. Then feed it a wrong input; confirm it fails loudly and instructively. Silent wrongness is a bug.

On the bench

Tracks in development.

Sign in and mark the ones you want first — you'll get an email the moment each is ready, and the queue tells us what to build next.

  1. 01

    AgentOps

    Operate agents in production on GCP. Agent SDK patterns, Cloud Run deployment, observability, evaluation harnesses, guardrails, and human-in-the-loop approval gates. Ship agents that don't quietly misbehave.

    Paid track · in development
    Early access
  2. 02

    On-Call Ready

    Cut time-to-response and time-to-action when you're paged. A Claude Code skill library for the common on-call moments: log triage, release reversion, cluster health checks, incident write-ups — ready the moment your pager buzzes.

    Paid track · in development
    Early access
  3. 03

    Job-description → track composer

    Drop in a job description. Get a composed track from existing lessons covering the core requirements, plus a gap list of what's missing. The gaps become the queue for what gets built next — driven by real hiring demand, not guesses.

    Feature · in development
    Early access

04

When the next thing you ship speaks for you, you're ready.

Browse courses