Articles

Superpowers uses a variety of skills to train AI from a 'coding intern' into a 'professional engineer'.

In this post, we'll add a simple RBAC (Role-Based Access Control) rule to blog-demo.

In this part, we'll do three things: integrate a minimal login system (Auth.js / NextAuth style) into the project; require users to be logged in for creating new articles and posting comments in blog-demo; and in API Routes, retrieve the current user ID from the session instead of using a hardcoded authorId.

In previous parts, we took a backend-focused approach with Prisma to build the data model and business logic for blog-demo. In this part, we integrate that model into Next.js to create a minimal yet complete personal blog admin panel.

In the previous article, we designed a set of relational models for blog-demo: User / Profile / Post / Comment / Category. It's functional, but still at the "structural level." In this section, I want to take a different approach: instead of explaining by concepts, I'll walk through a complete business workflow.

Starting from this chapter, we move from a single-table world with only User to a multi-table world with real business semantics: the blog-demo blog system.

The goal of this article is to break down the Prisma schema from top to bottom — explaining datasource, generator, model, enum, and all the attributes: what they are and how to use them.

In this article, we jump straight into a real project: using Prisma 7 + Next.js 16.2.2 + PostgreSQL + pnpm, we go from an empty directory to displaying the first User record from the database on the page.

Over the past year, AI has rapidly transformed from a 'tool' into a 'collaborator'. But many engineers, as they use it, gradually fall into a dangerous illusion: that AI can replace decision-making, even replace responsibility. The reality is quite the opposite. The more capable the AI, the greater the demand for humans to possess stronger constraint, judgment, and information-expression skills.

A Skill (or Skills) is a reusable skills package for AI agents—typically a folder containing task instructions, scripts, templates, and reference materials. The AI loads these resources on demand when handling relevant tasks, enabling more reliable and repeatable execution of specific work.