SEO Intel Blog · Use AI properly

What are Claude skills? What an AI skill is, what it's used for and how to create your own

The first time I got an AI to do a job really well, I saved the prompt in a notes file. The next week I couldn't find it, typed a shorter version from memory, and got a worse result. The week after that I typed a different version again.

Daryn Potgieter21 November 202611 min read

That's the problem a skill solves. A skill is that good prompt, written down properly once and kept where the AI can find it, so it does the job the same careful way every time.

This guide explains what a skill is, how it differs from the other things that get called "memory", and how to make your first one. You don't need to know any code.

What a skill actually is

A skill is a folder of instructions for one kind of job. At its heart is a single text file. The file says two things:

  1. When to use it. A short description, for example "use this when I ask for the monthly newsletter".
  2. How to do the job. The steps, the rules and the checks, written the way you'd brief a careful new member of staff.

A skill can also hold extra files the job needs: a template, a checklist, an example of a finished piece, or a small script. Anthropic describes skills as folders of instructions, scripts and resources that Claude loads when it needs them, to do a specific task in a repeatable way.

In Claude, skills are stored in your account. When you ask for something, Claude looks at the descriptions of the skills you have switched on, picks the one that fits and follows it. You don't have to paste it in or remind it. Anthropic describes it this way: Claude reviews available skills, loads relevant ones, and applies their instructions.

Skills vs prompts vs projects vs memory

These four get mixed up all the time. Here is the simple version.

What it is Think of it as
Prompt What you type in one chat A spoken request
Skill Saved steps for one kind of job, used whenever that job comes up A written method or recipe
Project A workspace with its own files and instructions, always loaded inside it A filing cabinet drawer for one piece of work
Memory What the AI keeps about you and your work between chats Notes about where things stand

The key difference between a skill and a project: a project's files are always there when you work inside it, but only inside it. A skill switches on only when the job needs it, and it works wherever you are. Anthropic's own help pages put it the same way: projects give background knowledge that is always loaded, skills give procedures that activate when needed.

Put simply: memory and projects tell the AI where things stand. Skills tell it how to do the job. You get the best results when you have both.

Skills vs MCP, agents, plugins and custom instructions

The other words you'll see, in plain English:

When to use a skill

Don't make a skill for one-off questions, or for facts that change often. Facts belong in memory.

What are Claude skills used for? Examples

Anything you do more than a few times, where you know what good looks like. Anthropic's own examples are applying brand guidelines, following a team's way of working and automating personal tasks. Some everyday examples:

Benefits of skills, and why to use them

Anthropic lists these benefits, and they match what I've found:

Why skills give better results than prompts

A skill doesn't make an AI perfect. It reduces drift and mistakes. Anything that matters still gets checked by you.

What a skill file looks like (an example)

In Claude, a skill's main file is a plain text file called SKILL.md, with the name and description at the top and the instructions underneath. Here is a made-up example for a small business newsletter. Yours will be different, but the shape is the same.

name: monthly-newsletter
description: Use when I ask for the monthly newsletter, the customer
email, or the "what's new" email.

Steps
1. Read the project's memory file first for this month's news.
2. Ask me for anything missing: offers, dates, new products.
3. Write a subject line under 50 characters and three options for it.
4. Keep the email under 250 words. One main message, one link.
5. Use UK spelling. No jargon. Sound like a person, not a brochure.
6. Check every date and price against what I gave you. If anything
   isn't confirmed, mark it [CHECK] instead of guessing.
7. Give me the draft. Never send it.
8. When I approve it, add one line to the memory file: date sent,
   subject line used.

Rules
- Never invent offers, prices or testimonials.
- If I say "no", ask what to change. Don't start again from scratch.

That's it. No code, just clear instructions. Notice the two things that make it work well: step 1 reads the memory file before starting, and step 8 updates it afterwards.

Pairing a skill with a good memory place

This is the part most guides leave out, and it's where the real gains are.

A skill on its own knows how to do the job but not what's happened so far. A memory file on its own knows where things stand but not the method. Join them up and the AI can pick up a job exactly where you left it.

The pattern I use:

  1. Every project has one memory file with a short "NOW" section at the top: what changed last, decisions made, what's next. (How to use AI properly shows how to set this up.)
  2. Every skill starts by reading that file. First step: "Read the project's memory file before starting."
  3. Every skill ends by writing to it. Last step: "Add what changed and what's next to the memory file."
  4. Rules live in one place. If a rule applies to every job ("never publish without my yes"), put it in your general rules file, not in every skill. If it only applies to one job, put it in that skill.
  5. Facts live in memory, methods live in skills. A price, a date or a decision goes in memory, where it's easy to update. The steps for a job go in the skill.

Get this right and the skill does the job the same way every time, using the latest facts every time.

How to create a skill (your first one)

You don't have to write it from scratch. The easiest way is to get the AI to write it with you.

  1. Pick a job you've done at least three times with the AI, where you know what good looks like.
  2. Do the job once more in a chat, correcting it until the result is right.
  3. Then ask: "Turn what we just did into a skill. Include the steps, the rules I gave you, the mistakes you made and how to avoid them, and when to use it."
  4. Read it through. Cut anything vague. Add anything it missed. Make sure it reads your memory file at the start and updates it at the end.
  5. Save it. In Claude, you can save a skill from the chat when it offers, or upload one under Customize, then Skills.
  6. Test it on a small job before trusting it with a big one.
  7. Improve it whenever something goes wrong. One new line each time.

The exact prompt we use for this is in the SEO Intel Skills and Prompt Pack.

Signs a job deserves a skill:

Do you need a paid plan?

No. Anthropic lists skills as available on the Free, Pro, Max, Ultra, Team and Enterprise plans. The one setting to check: skills need code execution switched on (Settings, then Capabilities on personal plans).

What a paid plan adds is mostly room. A long job that uses a skill uses up more of your allowance, so on a free plan you'll reach the limit sooner.

Do skills work in ChatGPT and Gemini? (Gems, projects and skills)

The idea works anywhere, but how you set it up differs.

In those, you may need to open the right project or Gem yourself rather than the AI choosing for you. Instructions written and tested for one assistant usually need a little adapting before they behave the same in another, so test on something small first.

Keep your skills learning: the weekly or monthly skill review

A skill doesn't learn by itself. It only changes when someone edits it. But your memory files are learning all the time: every session adds what happened, what was decided and what went wrong. The trick is to feed those lessons back into your skills on a schedule, so the skill gets better as you do.

This is the habit that made the biggest difference to my results.

What to look at. Once a week if you use a skill a lot, once a month if you don't, ask the AI to read:

What to ask. Ask the AI to compare the skill with what your memory files have learned, and to suggest changes without editing anything until you say yes.

The exact review prompt, which also handles saving the old version and logging what changed, is in the SEO Intel Skills and Prompt Pack.

What to change.

Keep a record. Save the old version before you change it (v1, v2, v3) and add one line at the top of the skill: the date and what changed. If a change makes things worse, you can go back.

Keep it small. A review usually means three or four lines changed, not a rewrite. If a skill needs rewriting every month, it's probably trying to do too many jobs. Split it.

The loop looks like this: do the work, save what happened to memory, review memory against the skill, update the skill, repeat. Your memory is where the learning is stored. The review is how the skill catches up.

Stay safe with skills

A skill is instructions your AI will follow, and some skills include small scripts. Treat them like any software:

Mistakes I made with skills

Quick start

  1. Pick one job you repeat.
  2. Do it once in a chat until it's right.
  3. Ask the AI to turn it into a skill.
  4. Add "read the memory file first" and "update it at the end".
  5. Save it, test it small, and add a line whenever it slips.
  6. Book a monthly review: check the skill against your memory files and lessons, and update it.

Skills aren't clever. They're just your best way of doing a job, written down once. That's exactly why they work.

Sources and further reading

Frequently asked questions

What is an AI skill?
A saved set of instructions for one kind of job. It says when to use it and how to do the job, and the AI follows it whenever that job comes up, so you get the same method every time.
What is the difference between a skill and a prompt?
A prompt is typed once in one chat. A skill is saved, used whenever the job comes up, and improved over time.
What is the difference between a skill and a project?
A project holds background files and instructions that are always loaded inside it. A skill holds the steps for one job and switches on only when that job comes up, wherever you are.
Do I need to know code to make a skill?
No. A skill is mostly plain written instructions. You can ask the AI to write it with you from a job you've just done together.
Are skills free in Claude?
Yes. Anthropic lists skills on the free plan as well as paid plans. Code execution must be switched on. Paid plans mainly give more usage.
Are skills safe?
Use skills from sources you trust, read them before switching them on, and never put passwords or payment details in one.
What are Claude skills used for?
Repeat jobs where you know what good looks like: writing in your voice, monthly reports, checking documents, job applications, customer replies and working with your connected apps.
What is the difference between a skill and MCP?
An MCP connector gives the AI access to an app or data. A skill gives it the method for doing a job, which can include how to use that connection. They work best together.
Is a skill the same as an AI agent?
No. An agent is an AI working through a longer task with tools. A skill is a set of instructions an agent, or a normal chat, can follow.
What is a skill file?
A plain text file, called SKILL.md in Claude, with a name and a description of when to use it at the top and the instructions underneath. It can sit in a folder with templates, examples or scripts.
Where can I find Claude skill examples?
Anthropic includes some ready-made skills in Claude, and there are public libraries online. Only add skills from sources you trust and read them before switching them on.
How often should I update a skill?
Add a line whenever something goes wrong, and do a proper review weekly for skills you use a lot or monthly for the rest. Check the skill against your memory files, decision log and lessons, and against any rule changes.
Do AI skills learn by themselves?
No. A skill only changes when it is edited. Your memory files capture what is learned, and a regular review feeds those lessons back into the skill.

Do it yourself. Skip the mistakes I made.

This guide comes from a real problem on one of my own stores. Here's how to skip it.

1

See what's wrong

Run the free store audit. No account, no card. Built for Shopify; Wix stores get a quick check too.

Run the free audit
2

Fix it yourself with Claude

Skills Pack (Shopify, £14.99): 8 Claude skills that check your store against Merchant Center rules and fix what they find, including suspension recovery.

Skills Pack £14.99
3

Learn how I did it

I cleared my own suspension without paying anyone. The full story, every mistake and every fix, is free to read.

Read how I did it