Ai-Agents

Someone writes a useful skill, it lives on their machine, and two weeks later a colleague solves the same problem from scratch. That is the pattern most teams fall into. The previous post covered how to write skills for Claude Code: a SKILL.md file that teaches Claude a workflow, living in your home directory where it applies to every project you work on, or committed to a project’s .claude/skills/ directory so everyone who clones the repo gets it too. Both setups work well within their scope. They break down the moment a skill needs to follow someone across projects, or reach a team that doesn’t share one repo. ...

AI coding assistants are powerful out of the box, but they have no memory of how you prefer to work. Every new conversation starts from zero. You explain your conventions, your preferred tech stack, your testing approach, and then you do it all over again next time. Skills attempt to solve this by letting you store reusable instructions that your assistant can draw on automatically. The concept was first introduced by Anthropic for Claude Code and has since been adopted by Google’s Gemini CLI and OpenAI’s Codex. All three follow the Agent Skills open specification, so the principles in this post apply regardless of which tool you use. ...