Claude Code on the web

Presentations and conclusion

Use Claude Code on the web to research one question and create an artifact. Each team member must complete this activity.

Connect GitHub

Open Claude Code on the web. If prompted, connect the GitHub account from Setup and give Claude access only to the repository where it will create the artifact.

Activity

  1. Select one research question from the list below. Each team member must select a different question.
  2. Paste the question into Claude Code on the web.
  3. Ask follow-up questions. Challenge unclear claims and verify the important parts of the answer.
  4. Ask Claude to create an artifact in the connected repository that explains your findings.
  5. Present the artifact to your group.
  6. Share the artifact on the course Padlet.

Optional extension: Create slides

Turn the artifact into slides. Start with the MARP template. You can also use the marp-slides skill.

The questions

  1. How do you wrap an API in an agent skill?
  2. How do you drive browser actions from Claude Code - the Chrome extension, a browser MCP, or a CLI tool? When is a browser the wrong tool for the job?
  3. How do you run an alternative model - Kimi K3, GLM 5.2, DeepSeek V4 Pro - inside Claude Code, and what degrades when you do?
  4. Pi ships a system prompt of about a thousand tokens and four tools; Claude Code ships far more of both. What do you gain and lose at each end of that spectrum?
  5. When should you use MCP vs agent skills vs CLI vs API?
  6. Explain the “smart zone” and “dumb zone” of the context window.
  7. Why would one use CLAUDE.md as a directory of links to other .md files instead of one large CLAUDE.md?
  8. What are the pros and cons of running coding agents (and models) on your own computer vs in the cloud?
  9. Find agent skills that review code quality, technical architecture, or security vulnerabilities. Compare and contrast them: what does each one actually look at, and where do they disagree?
  10. How should you format what you feed an agent - markdown, HTML, JSON, XML-style tags? Find a case where the format changed the answer.
  11. What is a sound decision-making process for choosing LLMs and inference providers?
  12. What happens when a tool result contains instructions aimed at the agent? Find a real prompt-injection case, and how harnesses defend against it.
  13. When does handing work to a subagent beat doing it in the main context - and when does it just cost more?
  14. What would you have to be sure of before letting an agent run unattended for an hour?
  15. How do you tell whether a prompt change helped, rather than just felt better?