Skip to content
Module
Module 2 of 5Lesson 2 of 3~15 min

Skill, CLAUDE.md, subagent, MCP or hook?

Skill, instruction file, subagent, MCP connector or hook: from a distance these mechanisms look alike, and the wrong choice complicates maintenance without meeting the need. This lesson helps you pick the right tool for each situation and defend that choice by weighing what each one brings and what it costs.

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

Lesson objective

By the end of this lesson, you will be able to choose, for a given need, between a skill, a CLAUDE.md, a subagent, an MCP server and a hook, and justify that choice by what each mechanism brings and costs.

Topics covered

  • skill vs CLAUDE.md
  • subagent
  • MCP server
  • hooks
  • Claude Code

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
  2. Skill, CLAUDE.md, subagent, MCP or hook? (this lesson)
  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