Skip to content

Skills

Skills are the most powerful way to teach Claude Code how to perform specific tasks your way: reviews, deployments, debugging, repetitive workflows... You define them once and Claude uses them when needed.

What is a Skill?

A Skill is a reusable set of instructions and procedures (checklists, multi-step workflows, specialized behaviors) that extend what Claude knows how to do. They follow the open Agent Skills standard plus Claude Code extensions.

Claude loads a Skill automatically when it's relevant (based on its description), or you invoke it manually with /skill-name. It can include auxiliary files: scripts, templates, reference documents.

Structure of a Skill

A Skill is a folder with a SKILL.md file inside. That file has two parts: YAML frontmatter (metadata) and a Markdown body (the instructions).

Terminal
.claude/skills/
└── deploy/
    ├── SKILL.md          ← instructions + metadata
    ├── checklist.md      ← auxiliary file (optional)
    └── scripts/
        └── deploy.sh     ← auxiliary script (optional)

SKILL.md example

Terminal
---
name: deploy
description: Deploy the application to production. Use it when the user asks to "upload", "deploy", or "push to production".
disable-model-invocation: true
argument-hint: "[environment]"
---

Deploy the application to the $ARGUMENTS environment following these steps:

1. Run the tests. If they fail, stop and report back.
2. Check that the branch is 'main' and up to date.
3. Run the production build.
4. Launch the deploy with the scripts/deploy.sh script.
5. Verify the site responds and summarize the result.

Frontmatter fields

Where they are stored

  • Personal (all your projects): ~/.claude/skills/<name>/SKILL.md
  • Project (recommended, versionable): .claude/skills/<name>/SKILL.md
  • Via plugin: inside the plugin, with a namespaced name like /plugin:skill
  • Monorepos: in subdirectories, qualified as /apps/web:deploy

How to invoke a Skill

Manually

Terminal
# No arguments
/deploy

# With arguments (passed as $ARGUMENTS)
/deploy production

Automatically

If you don't set disable-model-invocation: true, Claude will activate the skill on its own when your request matches its description. That's why the description is so important: write it with when it should be used in mind.

Create your first Skill (without knowing how)

Let Claude Code create it for you:

Included official Skills

Claude Code comes with ready-to-use skills. Some you'll see available:

  • /code-review — code review of the current diff.
  • /security-review — security review of your changes.
  • /init — generates your project's CLAUDE.md.

There is also a skill-creator plugin that helps you create, iterate on, and evaluate your own skills.

Live editing

You can edit a SKILL.md while Claude Code is open and the changes take effect immediately, without restarting. Ideal for refining a skill while you test it.

Complete Aulafy mapSee how this lesson fits without leaving your path.

Complete Aulafy map

How all courses connect

This is not a checklist. Start with the foundation, choose an outcome, and go deeper only when your project needs more control.

  1. 1Understand
  2. 2Apply or build
  3. 3Operate with confidence
01

Choose an application

Turn the foundation into a visible outcome: a website, a business improvement, media, or an interactive experience.

Continue into the technical branch when you need to maintain code, data, or infrastructure.

02

Build with code

Prepare your environment, work with coding agents, and run models while keeping control of your projects.

This branch prepares you to design and operate reliable AI systems.

03

Take systems to production

Combine retrieval, agents, evaluation, security, deployment, and model adaptation when the problem requires it.

You do not need every course: choose the component your system needs and return as it grows.

View full catalogue