Daniel Ávila

Claude Code is no longer just a coding assistant, it's becoming an operating system for software development. In this talk, I'll walk through how reusable templates, agents, hooks, skills, and MCP integrations can transform Claude Code into a structured, composable workflow engine. Drawing from building aitmpl.com and shipping these patterns in production at scale, I'll show how developers can stop prompting from scratch and start building on top of a shared, evolving component layer.

Claude Code is no longer just a coding assistant, it's becoming an operating system for software development. In this talk, I'll walk through how reusable templates, agents, hooks, skills, and MCP integrations can transform Claude Code into a structured, composable workflow engine. Drawing from building aitmpl.com and shipping these patterns in production at scale, I'll show how developers can stop prompting from scratch and start building on top of a shared, evolving component layer.

This talk dives into how developers can build structured, repeatable coding workflows using Claude Code's ecosystem: Skills, Subagents, settings, Hooks, and MCP servers. I'll walk through the architecture behind Claude Code Templates, an open-source project with 120K+ npm downloads and 23K+ GitHub stars, showing how these components work together to create composable, reusable patterns within real software development projects. From automating code reviews to orchestrating multi-agent tasks, we'll cover practical setups that teams can adopt immediately.

A technical breakdown of how the Claude Code Desktop runtime discovers, loads, and executes Skills. We'll cover the SKILL.md spec beyond the basics, frontmatter parsing, description-based triggering, file system scoping, and how skills compose with MCP and hooks in a single session.
Then the practical side: what makes a skill trigger reliably, how to scope it without bloating context, and the common failure modes when moving from CLI to Desktop.