Skip to content
Module
Module 2 of 5Lesson 1 of 3~14 min

What a skill is, and how Claude loads it

Pasting the same long prompt every time wastes time and gives uneven results from one conversation to the next. This lesson helps you understand what sets a skill apart from a simple instruction, how Claude decides to use it, and spot the tasks in your own work that truly deserve to become one.

Take this lesson: your first course is freeSee the full syllabus

Lesson objective

By the end of this lesson, you will be able to tell a skill apart from a one-off prompt, explain the three loading levels of a skill, and spot two tasks in your own work that justify creating one.

Topics covered

  • Claude Skills
  • what is a skill
  • progressive disclosure
  • reusable prompt
  • AI assistant

Where it fits

Understand skills and when to use them

What is a skill, how is it loaded, and when is it the right tool?

Lessons in this module

  1. What a skill is, and how Claude loads it (this lesson)
  2. Skill, CLAUDE.md, subagent, MCP or hook?
  3. Anatomy of a SKILL.md

What you will learn in the course

This lesson is part of the course Build reliable Claude Skills for your product work

  • Identify a recurring task that justifies a skill rather than a one-off prompt, and explain how the skill is loaded (progressive disclosure).
  • Choose and justify the right mechanism for a given need (skill, CLAUDE.md, subagent, MCP server, hook).
  • Write a name and description that trigger the skill at the right moment, and choose who can invoke it.
  • Design a complete SKILL.md (frontmatter, checkable rules, procedure, output format, reference files) from a scoping brief.
  • Configure a skill's pre-approved and removed tools according to risk, without confusing pre-approval with restriction.
  • Test a skill's triggering and output with evaluation scenarios, iterate, then measure its value over time.
  • Choose, audit and share skills (third-party or internal) while managing the security risks.

Related courses