How to install a Claude Code skill from GitHub
Install a Claude Code skill from any GitHub repo: the desktop steps, the two CLI commands, and why Claude keeps asking for permission afterwards.
Building with AI
Hands-on notes from building with AI since before GPT-3: machine learning and data, then LLMs, now agents.
Places to put the AI
Every product team building with AI faces the same question: where does the AI interaction go? Not the model or the prompt, but the affordance: the surface the user sees and interacts with. For my own reference and discussions I wanted to capture these. Even though the chat box is where this all got started, these are not stages of
Building a Google Slides renderer with coding agents
When I read about the Software Factory concept from StrongDM AI, I was intrigued. In part because of the ability to produce an impressively large and complex component. But even more so with how little it might take: could you really do that simply by taking pre-existing specs from the internet and have agents search the program space for
Search in program space
Coding agents run a search in program space. That's the closest analogy I can find for how to use agents productively. If you think of it as an assistant to whom you give tasks, you'll generally be in too tight a loop, giving feedback every few minutes. But the search analogy forces you to consider: 1.
Three categories of guardrails
There are only three categories of guardrails to prevent harm from agents. First, relying on hard constraints to only allow certain kinds of behaviour. For example, limiting which tokens can be decoded (structured output) or exposing only a specific set of tools to an agent. Assuming correct implementation, these guarantee certain behaviours won't be possible. Second, the LLM&
Agent skill - Statistics Estonia
Today I published my first agent skill: using Statistics Estonia databases. Often I have some simple question and I know data exists, but I can't be bothered to figure out the clunky UIs and directory trees and subtle variants of tables. This is now automated for me. It's built for Claude Code, but it works with
Claude Code IS the software
In 2024, humans created software. In 2025, Claude Code (and Codex, and Cursor, and all the others) created software. In 2026, Claude Code is the software. It's been clear for a while now that the cost of creating software has come down radically, so software becomes disposable: more like a paper towel than a CNC machine. It hasn&
Vibe coding a music learning app
Reading Shipping at Inference-Speed and with the Christmas holiday on my hands, I again felt a deep desire to ship a side project while getting a feel for state of the art AI coding tools. Usually I temper my enthusiasm for side projects and discard ideas immediately: rarely do I have significant free time on my laptop. But with
Skills, not agents
I used to think shipping an agent product meant building: 1. The core LLM loop. 2. Skills: describing to the LLM how to do particular things (including building API connectors etc). But it seems that Claude Code and Codex are strong enough general-purpose agents that you can just outsource (1) to one of those generic ones, and focus just
My deep research use cases
Deep research is underappreciated. The feature exists in all three LLM chat apps I pay for (ChatGPT, Claude and Gemini) and is unfortunately heavily rate limited, which makes sense given the likely token cost. But the massive amount of tokens burnt on reading and analyzing hundreds of articles is the reason it can have such a big impact on some