S2:E9

From Prompts to Agents: AI Agent Skills in Claude Code

AI
25 min

Host

Jonny DaenenJonny Daenen

Guest

Jesús García RamírezJesús García Ramírez

AI agents get messy fast once you move beyond simple prompts. Context windows fill up with noise, agents start reasoning in loops, and suddenly you're dealing with brittle behavior and hallucinations.

Jesus walks through how Claude Code skills fix this -- packaging repeatable workflows into modular components that load only when needed. He demos two real examples: an Explain Code skill and a PR Review skill that forks context, limits tool permissions, and uses CLI commands to analyze pull requests.

Read transcript →

Chapters

  1. 00:00Introduction
  2. 01:28Demo: Skills in Claude Code
  3. 05:57How agents work: from prompts to context engineering
  4. 08:19What are Skills? (vs MCP, RAG, Commands)
  5. 10:33Building your own Skill
  6. 15:20Skills vs MCPs
  7. 16:29What about hallucinations?
  8. 17:07Specs and Anthropic's Skill Guide
  9. 19:28Skillception: a skill to create skills
  10. 20:34Is MCP history?
  11. 22:50Sharing skills & wrap-up

Tags

Claude CodeAI Agent SkillsContext EngineeringSubagentsContext ForkingModular AI WorkflowsMCP vs SkillsClaude Code Tutorial

Listen on

Technologies

Claude CodeClaudeMCP

Additional material