Fabian Magrini | Blog

The rise of AI coding agents, like Claude Code, has fundamentally changed how we write, review, and ship software. But out of the box, even the most advanced models can lack the structured, context-aware workflows that seasoned engineers rely on. That’s why I created fabianmagrini/skills —my personal directory of custom skills designed to extend coding agents that support the Agent Skills standard . If you're looking to transform your AI coding assistant from a generic code-generator into a rigorous, end-to-end engineering partner, here is a look at what the repository offers and how you can use it to level up your workflow. What are Agent Skills? At their core, skills are reusable, invocable prompts that extend the capabilities of your coding agent. Each skill lives in its own directory and is triggered via a simple slash command. Instead of writing out a massive, detailed prompt every time you want your AI to perform a comp...

It is a tale as old as time in the software industry: Performance review season rolls around, your manager asks for your self-assessment, and you stare at a blank screen. You ask yourself, “What did I actually do this year, and what did my AI agent do?” We are living in an era where AI agents write the boilerplate, refactor legacy microservices, and churn through the Jira backlog. If you track your career the old way—by lines of code written or tickets closed—you are competing in a race to the bottom against a machine. To prove your value today, you need to prove your impact as an orchestrator, architect, and reviewer . You need empirical evidence of your systems-level thinking. Career advisors often suggest keeping a "Brag Doc." But for engineers navigating the AI era, that term feels outdated and ego-driven. Instead, you need a Growth Journal . A Growth Journal isn’t about boasting; it’s an enginee...

Skills are everywhere. Since Anthropic launched Claude Code , the ecosystem has exploded with custom "Skills"—directories of instructions and scripts that teach Claude how to handle specific domains. But there is a problem: almost nobody is testing them. Most developers "vibe-check" their skills with a few manual prompts, see a good response, and ship it. You wouldn’t ship a TypeScript library without a test suite, so why ship a Skill without an evaluation? This is a practical guide to fixing that. What Are Claude Code Skills? Agent Skills are folders that augment Claude's capabilities without retraining the model. They follow a progressive disclosure pattern, meaning Claude only loads the full instructions when it thinks they are relevant. At a minimum, a skill requires a SKILL.md file in .claude/skills/ : --- name: ts-zod-architect description: Use this skill when the user wants to define data models or API schema...

If you’ve been following the TypeScript ecosystem lately, you know we are standing on the precipice of the biggest shift in the language’s history. Microsoft has just announced the TypeScript 6.0 Beta (released Feb 11, 2026), and while it brings excellent new features, its true purpose is to serve as the final bridge to the revolutionary TypeScript 7.0 —the native, Go-based compiler rewrite known internally as "Project Corsa." In this post, we’ll break down exactly what is shipping in TypeScript 6.0, what the native future of TypeScript 7.0 looks like, and how you should prepare your codebase today. TypeScript 6.0: The Bridge to the Future Status: Beta available now ( npm install -D typescript@beta ); Stable release planned for March 17, 2026 . TypeScript 6.0 is a historic release. It is officially the last major version of TypeScript based on the original JavaScript/TypeScript codebase ...

Work in progress https://gist.github.com/fabianmagrini/27cf52240cd062f9b0c4b412797b84e9