Skills vs MCP: How AI tools have evolved

Eighteen months ago, MCP was the thing. Every demo and chatbot connector was running on MCP under the hood. When I started seeing everyone talk about Skills, I got curious. How are MCP and Skills connected? Are they different lenses on the same problem?

I brought these questions to @greggyb again in our latest video.

What's in the video

• What MCP actually does: giving a model programmatic access to APIs and the file system through natural language
• Downsides of MCP: context bloat from loading hundreds of lines of tool definitions for tools you're not even using
• What a Skill actually is (spoiler: pretty much a markdown file containing a reusable prompt)
• Progressive disclosure: why an agent can "know about" 20 skills without loading the full instructions for all of them
• Why MCP and Skills aren't competitors, and how Skills can even teach your agent how to use MCP tools

My favorite line from this one: the hottest programming language right now is English. Skills let non-developers write, iterate on, and share instructions that make an entire team's agents faster, no code required.

Are you using Skills yet? Curious where everyone's at.

Comments

[OrienSpec]

We can think of MCP as the kitchen tools and Skills as the cookbook.
The tools let you chop, mix, and cook, while the cookbook tells you what to do and when to do it. You need both to create a great dish—the tools provide the capabilities, and the skills provide the know-how.