Aulafy
ESEN
Courses
Courses/Claude Code, from zero to pro/Skills
Lesson

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).

TerminalCode
.claude/skills/
└── deploy/
    ├── SKILL.md          ← instrucciones + metadatos
    ├── checklist.md      ← archivo auxiliar (opcional)
    └── scripts/
        └── deploy.sh     ← script auxiliar (opcional)

SKILL.md example

TerminalCode
---
name: deploy
description: Despliega la aplicación a producción. Úsala cuando el usuario pida "subir", "desplegar" o "hacer deploy".
disable-model-invocation: true
argument-hint: "[entorno]"
---

Despliega la aplicación al entorno $ARGUMENTS siguiendo estos pasos:

1. Ejecuta los tests. Si fallan, detente y avisa.
2. Comprueba que la rama es 'main' y está actualizada.
3. Ejecuta el build de producción.
4. Lanza el deploy con el script scripts/deploy.sh.
5. Verifica que el sitio responde y resume el resultado.

Frontmatter fields

Where they are stored

  • Personal (all your projects): ~/.claude/skills/<nombre>/SKILL.md
  • Project (recommended, versionable): .claude/skills/<nombre>/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

TerminalCode
# Sin argumentos
/deploy

# Con argumentos (llegan como $ARGUMENTS)
/deploy produccion

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.

Technical playbooksSubagents