Claude Code Masterclass

Claude Code is part of Dr. Alfred Ang's everyday engineering toolkit, not just a subject to teach. Dr. Ang is a full-stack AI developer, Agentic AI solution architect and corporate trainer, and serves as CTO of Tertiary Infotech Academy Pte Ltd, the Singapore training organisation behind Tertiary Courses. Working across front end, back end, databases, cloud deployment and native mobile apps, Dr. Ang has published more than 300 public repositories on GitHub, many of them developed with agentic coding. Two repositories collect Claude Code skills that Dr. Ang wrote and uses: one auto-detects and starts any app, generates READMEs, pushes images to Docker Hub, drafts LinkedIn posts and scans for leaked secrets, while the other produces training slides, learner guides and lesson plans in a consistent house style. Dr. Ang also built a self-hosted AI-powered CMS on Next.js and the Claude Agent SDK, a Claude-powered courseware generator on Streamlit, and a course-proposal web app whose content generation is powered by Claude Code. The largest example is ai-mms, the course-registration LMS that runs Tertiary Courses' Singapore, Malaysia and Ghana sites, a mature PHP codebase that Dr. Ang maintains and extends with Claude Code alongside custom skills, hooks and project instructions. That mix of greenfield and legacy work informs everything in this masterclass. Daily use across very different codebases has given Dr. Ang a clear sense of what agentic coding does well, where it needs firm direction and how to structure instructions, skills and checks so that an AI collaborator stays productive rather than drifting into risky, unreviewed changes.

In the Claude Code Masterclass, Dr. Ang takes software developers, engineers, data professionals and technical leads from first install to real productivity. The opening topic covers getting started: setting up Claude Code in the terminal and IDE, writing a project instructions file, and learning how Claude navigates a codebase, edits files and runs commands while the developer stays in control. The second topic explores agentic development workflows, including planning before coding, breaking work into reviewable steps, running tests in the loop and using version control safely so changes stay small and easy to audit. Topic three extends Claude Code with hooks, skills and MCP servers, and here Dr. Ang shares lessons from building and using custom skills daily, such as when a skill beats a long prompt and how hooks can enforce checks automatically. The final topic puts everything together on real-world projects, where participants build or refactor an application end-to-end with Claude Code doing the heavy lifting. Dr. Ang is candid about failure modes too, showing how to verify output, recover from a wrong turn and avoid letting an agent make unreviewed changes. The class is hands-on throughout, with live coding and time to apply each technique to learners' own repositories. Particular attention is given to team adoption, including sharing project instructions and skills across a team, agreeing review standards for AI-written code and keeping secrets and production systems protected, so that the productivity gains seen in class translate into safe, repeatable practice back at work. Browse Dr. Ang's Claude Code skills and projects at https://github.com/alfredang.