Claude Skills are reusable work instructions for Claude: you write down once how a specific task is supposed to run, with your steps, your rules, your examples. From then on, Claude applies that instruction automatically whenever the task comes up. You no longer prompt the process from scratch every time; it's infrastructure.
For me, Skills are one of the three reasons my entire AI workforce runs on Claude. The other two, and all my other guides, are on my Claude overview page.
What a Claude Skill is
Technically, a Skill is a folder with a file called SKILL.md. It describes, in plain text, when the Skill applies and how the task runs. Templates, reference material, and small helper scripts can be added. Claude only loads the Skill when it's needed and then works through the instruction step by step.
The crucial part isn't the tech, it's the format: a Skill is a readable document. You can open it, understand it, and change it like a work instruction for a person. No flowchart, no code you can't see through.
Anthropic ships some Skills preinstalled, for example for Excel spreadsheets, Word documents, PowerPoint presentations, and PDFs. But the interesting Skills are the ones you write yourself.
Installing and activating Claude Skills
Here's how to get Skills (as of August 2026, Skills are available on all plans including Free):
- In the Claude app: Enable the code execution feature under Settings, then open the Skills section under "Customize." There you can switch on existing Skills or upload your own.
- Uploading your own Skills: A Skill is uploaded as a ZIP file. The folder contains the SKILL.md, and the folder name has to match the Skill name.
- In Claude Code: Skills live as folders in your Skills directory and are detected automatically. You can invoke them directly with a slash command, such as
/create-proposal.
On Team and Enterprise plans, Skills can additionally be shared with colleagues or the whole organization.
Creating Claude Skills: write a work instruction, not a program
This is where most guides on the internet fail, because they treat Skills like a developer topic. My advice: forget the tech for a moment and imagine you're writing a work instruction for a new employee. That's exactly what a Skill is.
A good work instruction answers four questions:
- When does it apply? "Whenever a proposal draft is created."
- What are the steps? In order, concrete: first read the inquiry, then match the services, then write the draft, then check it against the checklist.
- Which rules apply? Phrases that always have to be included. Phrases that must never appear. What gets submitted for approval.
- What does a good result look like? One real example says more than ten rules.
The easiest way to your first Skill: let Claude write it itself. Once you've walked through a task cleanly in a chat and the result is right, say: "Turn this process into a Skill so you work exactly the same way next time." Then you proofread the result and correct what's off.
Three example Skills to get started
To make this tangible, here are three sketches of what such work instructions can look like:
1. Proposal Skill. Applies when a client inquiry is supposed to become a proposal. Steps: summarize the inquiry, pull the matching services and prices from the personnel file, write the draft in your own voice, collect open questions for the boss. Rule: no proposal leaves draft status without approval.
2. Content review Skill. Applies before every publication. Steps: check the draft against a list of your own rules, such as hook quality, banned filler phrases, length. Violations get flagged, not silently rewritten. That's how my content editor-in-chief works: every draft runs against my hook rules before I even see it.
3. Weekly report Skill. Applies every Friday. Steps: collect completed tasks from the work folders, list open items, make three suggestions for next week. Result: half a page, always structured the same way.
You'll notice the pattern: a Skill is always a process you'd otherwise explain out loud. If you could teach it to an intern in five minutes, you can write it down as a Skill.
Three mistakes that make Skills useless
After many work instructions written and thrown away again, I know the typical traps:
- Too vague. "Write good proposals" isn't a Skill, it's a wish. A Skill needs verifiable steps and rules. If you can't tell whether Claude followed the instruction, it's worded too softly.
- Too long. A Skill that tries to cover every edge case becomes a novel nobody maintains anymore. Write down the normal case and only add edge cases once they actually occur.
- Skills for one-off tasks. A Skill only pays off for processes that recur. For a one-time task, the chat is enough.
The rule of thumb: a Skill is good if you open it in two months and immediately understand what it does and why.
Why Skills make the difference
Without Skills, an AI gives you a slightly different version of the task every time, depending on how you happened to prompt. With Skills, you get repeatability: the task runs the same way next week as it does today, and when you want to change something, you change a document instead of your prompting habits.
That makes Skills the second of the three puzzle pieces in my approach: the Claude Project as personnel file holds who your employee is and what they know. Skills hold how they work. And feedback flows into both instead of vanishing in the chat history. Why exactly this combination brought me to Claude is covered in Claude over ChatGPT.
Where to start
Take a task you're doing with AI this week anyway and walk through it once cleanly in a chat until the result is right. Then have Claude turn it into your first Skill and proofread it. That's all it takes to get started.
If you want to set the whole thing up properly from the start, with a role, personnel file, and onboarding instead of individual Skills: the complete process is in Hiring an AI employee.
