weinzierl

Claude Skills are awesome, maybe a bigger deal than MCP

https://simonwillison.net/2025/Oct/16/claude-skills/

Claude Skills are awesome, maybe a bigger deal than MCP

Anthropic this morning introduced Claude Skills, a new pattern for making new abilities available to their models: Claude can now use Skills to improve how it performs specific tasks. Skills …

Simon Willison’s Weblog
Oct 17 at 5:40pmWeb
Show threadtptacekOct 17
I do think the big story here is how hyperfocused and path-dependent people got on MCP, when the actually-interesting thing is simply "tool calls". Tool calls are incredibly interesting and useful. MCP is just one means to that end, and not one of the better ones.
Show threadkasey_junkOct 17

MCP seems valuable in that it teaches the llm about oauth. So you can do server based tool calls.

Before that you had to install each cli you wanted and it would invariably be doing some auth thing under the covers.

Took calling was certainly the big llm advantage but “hey tools should probably auth correctly” is pretty valuable.

Show thread3abitonOct 17
I would argue MCP is technically a "tool calling" approach, albeit more specific.
Show threadtptacekOct 17
It is, it's just a very specific approach, and it's simultaneously a bit underspecified and a bit too prescriptive.
Show threaddidibusOct 18

> Tool calls are incredibly interesting and useful. MCP is just one means to that end, and not one of the better ones.

It's nice to have an open standard though. In that sense it's pretty awesome.

But MCP isn't just tools, you can expose prompt templates and context resources as well.

All the skills that don't have an added dependency on a local script could just be an MCP resource.

Show threadtptacekOct 18
You don't need MCP for prompt templates and context resources. Those are both just forms of prompting.