Claude Skills are awesome, maybe a bigger deal than MCP
simonwillison.netAs someone who is looking into MCP right now, I'd love to hear what folks with experience in both of these areas think.
My first impressions are that MCP has some advantages:
- around for longer and has some momentum
- doesn't require a dev envt on the computer to be effective
- cross-vendor support
- more sophistication for complex use cases (enterprise permissions can be layered on because of OAuth support)
- multiple transport layers gives flexibility
Skills seems to have advantages too, of course:
- simpler
- easier to iterate
- less context used
I think if the other vendors follow along with skills, and we expect every computer to have access to a development environment, skills could win the day. HTML won over XML and REST won over SOAP, so simple often wins.
But the biggest drawback of MCP, the context window overuse, can be remediated by having MCP specific sub-agents that are interacted with using a primary agent, rather than injecting each MCP server into the main context.
I hope we move to a world where things like Skills replace MCP. People could package scripts that make API requests with curl instead of providing custom MCP servers. I think this has the potential to be much more flexible than MCP, make use of existing REST API infrastructure, and have much better context characteristics for agents.
MCP can be very clunky, both in it polluting your context and it being annoying to set up new services. Skills are simpler and put more work on the agentic harness, which I like.
Even before "Skills" I found that if you could write bash scripts for agents to execute instead of running MCP servers, that would often work a lot better. It's not always easy for things like controlling a browser, but when it does work bash scripts can be much simpler to manage. Skills are effectively an extension of this idea, just with nicer context management built-in.