MCPs vs Agent Skills: Understanding the Difference
MCPs give Claude capabilities. Skills teach Claude workflows. Here's the mental model I use to decide which one I need.
Hi, my name is
I help experienced engineers and teams ship better software with AI, smarter workflows, and real-world decision-making.
Currently a Senior Software Engineer at August Health, where I build clinical software that helps senior living operators deliver better resident care. Previously CTO at Buoy Software, where I grew the team from zero to 50+ and shipped FDA-cleared medical device software.
I advise founders and teams on architecture, AI integration, and engineering execution. 15+ years building production systems has taught me that trade-offs matter more than best practices — and I enjoy helping teams navigate those decisions.
If you're building in healthcare, SaaS, or applied AI, I'd love to hear about it.
Writings
MCPs give Claude capabilities. Skills teach Claude workflows. Here's the mental model I use to decide which one I need.
LLMs don't have access to the current date, causing issues in time-based analysis. Here's how to fix date and time handling in production LLM systems with explicit context.
How Claude Code's context window works: what consumes tokens (MCP servers, tools, messages), why it matters, and how to manage context effectively.
After 8 months with Claude Code, here's my complete workflow. Learn how I combine Linear, MCP servers, and Obsidian for AI-assisted development that works.
Three design principles for context-efficient MCP servers: filter at source, pre-aggregate data, work creatively. Real reductions: 746k→262 tokens.
Customer obsession can sharpen focus and drive urgency—but left unchecked, it burns out teams and breaks products. Here's how to get it right.