AI Without the Hype.
Chapter 8 of 21
Part Three · Make It Yours · Chapter 08

What a Skill is

By the end of this chapter you can tell the difference between a rule that is always on and a skill that is pulled in when needed, and you can build your first skill by talking it into existence.

Your CLAUDE.md sets rules that apply to everything in a project. But some jobs are not always-on. They are recurring: the way you write a weekly update, the steps you follow to prep a client call, the exact shape of a good invoice. You do not want those rules cluttering every conversation. You want them to show up only when the job comes up. That is a Skill.

A Skill is a job you teach the AI once so it can do it the same way every time, without you re-explaining the steps. Where CLAUDE.md is the standing law, a Skill is a saved recipe the model reaches for when the moment matches. Teach it once, reuse it forever.

AVATAR OPENER · ~90s
Watch: teaching a recurring job once instead of re-explaining it every week
HeyGen avatar · generated, consistent presenter

The cleanest way to hold the difference: CLAUDE.md is pushed at the model, always present in the background. A Skill is pulled in, only when it is relevant. You would not want every recipe in your kitchen taped to the fridge door at once. You want them filed, and the right one in your hand when you are cooking that dish.

VS
CLAUDE.md is pushed at every task. A Skill is pulled in when the job appears. You would not tape every recipe to the fridge. You file them, and reach for the right one when you cook that dish.
HOW A SKILL GETS MADE

Here is the part nobody tells beginners. You do not write a skill by hand. You build it by talking. Claude has a skill that helps you make skills, and it interviews you: what is the job, when should it trigger, what are the steps. You answer in plain words and it writes the recipe with you.

Name the job
Tell it the recurring task you keep redoing.
It interviews you
When should this trigger? What are the steps?
It drafts the recipe
A plain-text skill file, written with you.
You test and keep
Try it on a real case, fix a line, save it.
SEE IT

You do not need to know the format. You just describe the job clearly. Here is the kind of thing you say to start, for a consultant who writes the same style of weekly client update every Friday.

Starting a skill by talking
Help me make a skill for a job I do every week. The job: writing my Friday client update. It should trigger when I say "draft this week's update". The steps I always follow: 1. Pull the three things we shipped this week. 2. Name one risk or blocker honestly, no spin. 3. End with what happens next week. Keep it short, plain, and never over-promise. Interview me if anything is unclear, then draft the skill.
Try it in Claude

One quiet lesson worth keeping from how skills work: the description of when a skill should trigger matters as much as the steps inside it. A skill with a vague trigger never fires when you need it. A clear trigger (the exact phrase, the exact situation) is what lets the model reach for the right recipe at the right time. Good descriptions are not decoration. They are what makes the thing reliable.

Skills in this exact form are one of the more Claude-specific things in the course, so here is the honest portability note. The other tools have cousins, not copies: ChatGPT has custom GPTs and Gemini has Gems, both reusable configured assistants you set up once. They are not identical to a pull-in-when-needed skill, but the instinct transfers: spot a job you repeat, teach it once, reach for it by name. If you move tools, you keep the instinct and learn the local version.

NOW YOU TRY · CREATE
Build your first skill by talking

Pick one job you genuinely repeat: a weekly update, a standard reply to a common question, the way you outline a video, your invoice format. Ask Claude to help you make a skill for it. Let it interview you. Name a clear trigger phrase and the steps you actually follow. Then test it on a real instance and fix one thing.

Right if running your trigger phrase produces the job done in your steps, without you re-explaining the process.
Show the worked solution
The win is the second time you use it. The first time feels like a long conversation: you describe the job, it asks clarifying questions, you answer, it drafts. That is normal, that is the teaching. The payoff is the next Friday, when you type your trigger phrase and the whole process just runs, in your style, without you listing the steps again. Take the consultant’s weekly update. A weak skill triggers on something vague like "updates" and fires at the wrong moments or not at all. A strong one triggers on the exact phrase "draft this week’s update" and carries the real steps: three shipped things, one honest risk, what is next. If your skill did not fire when you expected, the trigger was too vague, so sharpen it. If it fired but did the job wrong, the steps were thin, so add the detail you skipped. One example skill, built by talking, is the whole lesson. You do not need ten.
WATCH FOR
You try to write the skill file by hand. Do not. Describe the job and let Claude interview you and draft it.
You give it a vague trigger. A vague trigger never fires. Use the exact phrase or situation that should set it off.
You make a skill for a one-off task. Skills are for jobs you repeat. A one-off is just a normal request.
You expect it perfect on the first try. Test it on a real case, fix the line that was off, and it gets sharper with use.
WHAT YOU LEARNED
The takeaways
  • A Skill is a recurring job taught once, so the model does it the same way every time without you re-explaining the steps.
  • CLAUDE.md is pushed (always on); a Skill is pulled in only when the job appears.
  • You build a skill by talking. Claude interviews you about the job, the trigger, and the steps, then drafts the recipe with you.
  • The trigger description matters as much as the steps. A clear trigger is what makes a skill fire reliably.
Your project · step eight

Find one job inside your thread project that you already repeat, and turn it into your first skill. Now your project has three layers: a constitution (who you are), a CLAUDE.md (how this project behaves), and a skill (a job it can do on command). That is a real system, built by you, in plain language. Next: how to hand it bigger work and stay in control.

You used to re-explain the same job every week. Now you teach it once and reach for it by name. That is the difference between using a tool and owning one.