Short CourseBeginner

Agent Skills with Anthropic

Instructor: Elie Schoppik

Anthropic logo
  • Beginner
  • 10 Video Lessons
  • Instructor: Elie Schoppik

What you'll learn

  • Create reusable skills using the open standard format and best practices, and compose them to create complex workflows.

  • Build custom skills for code generation and review workflows, data analysis, and research that your agent loads on-demand.

  • Combine skills with MCP and subagents to create powerful agentic systems with specialized knowledge and access to external data sources.

About this course

Join this new short course on Agent Skills, built in partnership with Anthropic and taught by Elie Schoppik.

Skills are folders of instructions that extend agent capabilities with specialized knowledge. Instead of repeatedly explaining the same workflow, you can package it as a skill so your agent automatically knows what to do. Because skills follow an open standard format, you can build them once and deploy across any skills-compatible agent.

In this course, you’ll learn how skills work, explore best practices for creating them, and build skills for different use cases. You’ll see skills in action across Claude.ai, Claude Code, the Claude API, and the Claude Agent SDK, and learn how to combine them with MCP and subagents for complex workflows.

In detail, you’ll:

  • Understand how skills transform general-purpose agents into specialists when needed.
  • Learn the structure of a skill folder, the format of SKILL.md file, and how skills use progressive disclosure to manage context efficiently.
  • Understand how Agent Skills compares to tools, MCP, and subagents.
  • Explore Anthropic’s pre-built skills for Excel, PowerPoint and Skill Creation, and use them with Claude.ai to build a marketing campaign analysis workflow.
  • Create custom skills following best practices: build skills for generating practice questions from lecture notes and analyzing time series data characteristics.
  • Use custom and pre-built skills with the Claude API, by integrating the code execution tool and files API to equip Claude with filesystem access and bash for executing python scripts.
  • Build code generation, review, and testing workflows with Claude Code using skills, and set up subagents equipped with skills for specialized tasks with isolated context.
  • Create a research agent using the Claude Agent SDK that leverages a skill to generate a learning guide for an open-source tool based on its documentation, GitHub repo, and web search.

Whether you’re automating code reviews, standardizing data analysis workflows, or building research agents, this course gives you hands-on experience creating skills that make general-purpose agents more reliable and capable.

Who should join?

Any AI builder who wants to extend agent capabilities with reusable workflows and specialized knowledge.

Course Outline

10 Lessons・0 Code Examples

Instructor

Elie Schoppik

Elie Schoppik

Additional learning features, such as quizzes and projects, are included with DeepLearning.AI Pro. Explore it today

Want to learn more about Generative AI?

Keep learning with updates on curated AI news, courses, and events, as well as Andrew’s thoughts from DeepLearning.AI!