Nobody knows what's going to happen.

Claude Skills

I’m late to Claude Code. So it’s not news to say Skills is leap forward. From Ethan Mollick:

Users have to prompt AIs to do things.

These prompts act as instructions, and, as AIs have gotten smarter, they have become much better at executing complex prompts, even hundred page long prompts.

These long prompts take up a lot of the context window, however, and require a giving the AI the right prompt at the right time.

That either means that you, as a human, have to keep prompting the AI or you have to design a complex automated system that keeps feeding the AI prompts.

Skills solve this problem.

They are instructions that the AI decides when to use, and they contain not just prompts, but also the sets of tools the AI needs to accomplish a task.

Does it need to know how to build a great website?

It loads up the Website Creator Skill which explains how to build a website and the tools to use when doing it.

Does it need to build an Excel spreadsheet? It loads the Excel skill with its own instructions and tools.

It is like when Neo in the Matrix gets martial arts instructions uploaded to his head and acquires a new skill: “I know kung fu.”

Skills can let an AI cover an entire process by swapping out knowledge as needed.

For example, Jesse Vincent released an interesting free list of skills that let Claude Code handle a full software development process, picking up skills as needed, starting with brainstorming and planning before progressing all the way to testing code.

Skill creation is technically very easy, it is done in plain language, and the AI can actually help you create them.

Anyone can share Skills or subagents, and companies who want AI agents to work with their products can use an approach called the Model Context Protocol (MCP) to give any AI instructions and access.

There are MCPs from publishers that let AI access scientific papers for research, MCPs from payment companies that give the AI the ability to analyze financial data, MCPs from software providers that let AI use a particular software product, and so on.

The result is a very flexible system where a smart generalist AI like Claude Opus 4.5 can apply specialized skills on the fly, use tools as needed, and keep track of what it is doing.

But.

Be careful with Claude Skills. They are super powerful. Bad actors can hijack a skill with an embedded, hidden prompt inject, so be sure to only use 100% trusted skills, even if they look fully legitimate.

Leave a comment