⭐ Find Skillgrade on GitHub skill grade A few weeks ago I wrote about Skill Eval, a framework for testing AI agent skills. The idea resonated — skills are becoming a critical part of how teams work with agents, and without a way to measure whether they work, you’re guessing.
The problem was that Skill Eval required too much setup. You had to clone a repo, understand a specific directory structure, write TypeScript config, and wire everything together before you could run your first eval.
- ⭐ Find Skill Eval on GitHub Unit Tests for AI Agent Skills I’ve been working with AI coding agents daily - Antigravity, Gemini CLI, Claude Code, and others. One pattern I keep seeing is teams building skills for these agents: procedural instructions that teach the model how to use internal tools, follow specific workflows, or comply with team conventions. The problem? There’s no way to know if they actually work.
- In conversations with developers lately I’ve been noticing a lot of discomfort when bringing AI. Talking to people and doing self-reflection I think there are a couple of reasons for this: Overinflation. AI is certainly over hyped by some. People have business interests in raising money or increasing the valuation of their companies and they tend to exaggerated the capabilities of agents and language models. This makes it feel like we’re in yet another hype cycle that will pass, so why waste energy?
- Historically in my blog I’ve been posting 10-20 page deep-dive explorations in type theory, deep neural networks, predictive prefetching, etc. Recently, I’ve been thinking of taking a new approach with short snippets based on my current thinking about a particular topic. Today, I’ll share high-level takes on developer workflows and how they can impact the tools we use. LLMs enable velocity We can certainly speed up our developer velocity using GenAI.
- The opinions stated here are my own, not necessarily those of my employer. Over the past few weeks I’ve been thinking about how we can make a framework easier for AI. In particular I’ve been only focused on building user interface. When we add a backend, database, and communication protocol across the backend and the frontend, we get another set of problems that could be a good fit for another post and exploration.
- One of my current projects is converging Angular and Wiz into the same framework. This is a complex projects that involves a lot of work and many people. It also got me thinking about different client-side rendering models. In this blog post I’ll show a very simple library that enables you to develop components with fine-grained reactivity. To make it easier to talk about this library, I called it “revolt.”
- Over the past couple of years, I’ve been the product lead for Angular. In this article, I’d like to share how we’ve been managing the framework. Keep in mind this content lives on my personal blog for a reason - it represents my point of view and doesn’t share a complete picture of all the processes within the team, such as people management, program management, etc. Also, that’s the second time I’m writing this article.
- Over the past few years, I have published most of my posts on blog.angular.dev and my blog has received little attention. Today, I decided to share something that has been on the mind lately. It’s inspired by a mixture of one of the most memorable moments from my university classes and the recent boom of AI. Through the lens of the theory of computation I’ll attempt to answer the question, “Are we going to be replaced by AI?
- In this post, we’re going to focus on web performance. In particular, we’ll be discussing optimizing user experiences preemptively. When it comes down to speeding future actions up in Web UI development, we usually apply prefetching. With prefetching, we download and cache resources relying on assumptions for the user’s behavior. This way, we proactively perform a slow operation that the user would eventually have to execute while interacting with the app.
- This blog post introduces another design pattern into the context of ngrev. If you’re not yet familiar with the project, I’d strongly recommend taking 2 minutes to the introduction and “Project Overview” sections in the first part of the series. If you did not take the time, ngrev is an Electron app that visualizes the structure of an Angular app, showing the relationships between components, modules, and providers. The UI retrieves the data for each view using an instance of a state object.