Behavioral Annotations: Why readonly and destructive guide LLM Planning
6d ago · 4 min read · In a previous post, we discussed how Schemas act as the "Postman" of the apcore ecosystem—ensuring that data is delivered in the correct format. But knowing how to deliver a message isn't enough for a
Join discussion
Getting started with agent-skills can be an exciting venture, especially for developers looking to create intelligent agents that can perfor
Mar 7 · 5 min read · Introduction Getting started with agent-skills can be an exciting venture, especially for developers looking to create intelligent agents that can perform various tasks. Agent-skills is a framework that enables developers to build, deploy, and manage...
Join discussionShip 10x Faster: The Exact AI Stack I Use to Build Frontend Projects in 2026
Mar 6 · 14 min read · I'm going to say something that would've gotten me laughed out of a standup meeting two years ago: I don't write most of my frontend code anymore. I architect it, review it, steer it, and ship it — bu
Join discussion
Going a step further than Agent Skills. Introducing Agent Apps — A new interface paradigm where LLM agents are first-class citizens.
Mar 5 · 8 min read · Rethinking UI for the Age of AI Agents For decades, user interfaces have been designed exclusively for humans — graphical, interactive, and optimized for eyes and hands. But as Large Language Models (
Join discussion
Upskilling Antigravity for the Gemini API
Feb 17 · 2 min read · Google Antigravity is an agentic IDE that helps you build software. Antigravity offers a variety of models for agentic coding including the latest Gemini and Claude models. If you’re building an app that calls the Gemini API, you may find that the ge...
Join discussion
Anatomy of an Agent Skills
Feb 9 · 3 min read · Agent Skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows. At its core, a skill is a folder containing a SKILL.md file. This file includes metadata (name and description, at minimum) and ...
Join discussionAgent Skills & AaaS: AI’s Universal Adapter & On-Demand Agents
Jan 26 · 9 min read · Stop me if this sounds familiar: You’re in the middle of a high-intensity "vibe coding" session, feeling like a digital god, until your AI assistant confidently suggests a library version that hasn't been relevant in a while. Suddenly, the flow is de...
Join discussion
Skills, Agents, and the Missing Middle
Jan 9 · 4 min read · If you’ve been building with LLMs for a while, you’ve probably built an agent at some point. You give the model a role. You add a few tools. You maybe throw in memory, some planning logic, and a carefully tuned system prompt. It works. Until it doesn...
Join discussion
Why I Reach for Skills Before MCP
Jan 8 · 3 min read · There's been a lot of discussion lately about skills vs MCP—whether they're complementary, competing, or if one makes the other obsolete. I've built both—an MCP server for Maven Central and a collection of skills for various dev tasks. After using bo...
Join discussion
