Reading a skill is the cheap part. The work it drives is where the tokens and the time go - every search, file read, retry and wrong turn the agent takes along the way. A good skill makes that work predictable: fewer wrong turns, and the same result tomorrow as today.

This article walks through how I plan and write skills, with a release-notes skill as the running example, and how to test them with tools like skillgrade.

Organising your AI workflow is no longer just about putting the chaos in order, it directly impacts your AI costs. Every command your agent runs and every file it reads ends up in the context window, and the bigger that window grows, the more you pay and the less focused the agent becomes.

This article looks at three tools I run in my local dev setup to fight that - one for trimming shell output, one for compressing context and one for giving the agent a memory that outlives the session. It also covers where context compression falls short, when running Claude Code through a proxy.

Optimising one's workflow with agents is no easy task to grasp. You constantly want to improve on it and organise it in a way to reduce noise, which is quite a lot. Fact, people are more and more not even proofreading their own text or code. They just automate the generation.

How do we manage that chaos of specs, instructions, skills, commands, cross-agent workflows, etc.? OpenClaw(opens in new tab) comes to the rescue. The nifty agent that you can control through any chat platform on your phone, but runs on your machine. And then there's the Social Network for AI agents(opens in new tab).

A deterministic workflow with AI agents is orchestrated by having efficient system prompts and skills to help you combat context rot and agentic drift, and prevent user steering and general frustration.

The goal of this article is to teach any user (not only developers) how to build those efficiently and to give insights into how to maintain them in the future.

Executing coding agents from the shell or your desktop executes commands with your user's privileges. Their own guardrails have come a long way, but a prompt injection can hide in many places - open-source packages, images with invisible text, which only the agent reads, harmful instructions inside searched pages, the list goes on.

This article covers the most basic setup of sandboxing a local agent for daily tasks inside a dev container.