Anthropic published a thoughtful guide to making skills. It is worth reading, but it's a map of work you should not have to do.

The Claude Code team wrote a piece on how they use agent skills. If you make skills, read it. It is honest and tells you something important: making a good skill is real work.

Here's what the guide covers. It sorts skills into nine categories. It explains progressive disclosure, where the agent knows which files to load and when. It covers scripts, config files, combining skills together, and writing the description so the model reaches for the skill at the right moment.

All of that is true and useful. It is also a lot to learn. And most of it exists only because you are doing the work by hand.

We're SkillsCake. We make and score agent skills all day. So we read this guide a little differently than someone meeting skills for the first time. Here's what we think.

Skills are infinite

The guide splits skills into types: library reference, verification, and so on. That is a helpful way to teach a class. It is not what a skill actually is.

A skill is prose that tells an agent how to do one thing, sometimes with scripts attached. The set of possible skills is not nine boxes. It is every job you could describe in writing; it's infinite. Categories are how a person gets a handle on something that open-ended. They are scaffolding for learning, not the shape of the thing.

This matters because the moment you think in categories, you start bending your skill to look like the example in its bucket. Your real job rarely fits the bucket. The best engineered skill is the one written for your exact task, by an expert.

Doing it yourself might not be worth it

Progressive disclosure, scripts, config, descriptions tuned for the model, gotchas earned by failing, and eval loops: none of that is busywork. It's how a good skill gets built by hand. The guide is not overcomplicating anything. It is being honest about what the manual path costs.

But that is the point. Every hard part in the guide is hard because a person is doing it. You are learning to write prose for a machine reader, a skill almost nobody has yet. You are writing scripts, testing them, and collecting gotchas the slow way, by hitting them. Anthropic has a team and the tooling to do this well, but you would have to sacrifice other work just to upskill your Copilot or Claude.

Let SkillsCake read the guide instead

The SkillsCake team puts in the work, just like the Claude Code team. But we do it for your AI skills.

We teach SkillsCake, the skill improver, what actually works: the structure, the descriptions a model triggers on, the gotchas, the eval loops the guide walks through. We've run evals on skills across disciplines. We build skills for planning complex projects, weekly spreadsheet updates, deploying microservices to the cloud, and planning meal preps. Every part of upgrading skills is built into how we work, and it's built into the pipeline that makes a personalized, secure, repeatable skill for you in minutes. All so it doesn't have to eat into your attention.

Here's how SkillsCake thinks about making a skill: A skill is prose engineered for one task and one person. SkillsCake can bake a perfect skill the way an expert writes for a job they know cold. The guide teaches you to do that by hand.

Want to try SkillsCake? Give us a skill, or describe the one you want, and tell us in the notes how it should be yours. We bake the rest.

The guide is great, and it shows how early this is

You're early—making a skill still needs a guide this thorough. Skills are so powerful. But they're mostly manual.

That stage won't last. We'll make sure we're the ones to democratize skills, and we'll keep you updated so you don't get left behind.

Originally published on the SkillsCake blog.