Actually you just need a prompt and some tools

Skills are basically just a prompt and (optionally) some tools, only with a preamble that means they are selectively brought into context only as needed.

Claude Skills are just good documentation wrapped into Anthropic's API in a proprietary way that's designed to foster lock-in.

How are skills vendor lock-in when they're just Markdown files that any LLM can read? You are not locked to Anthropic at all.

The API runs your skills, it's not client side coordinated. You have to replicate the skill-running behavior locally.

Claude just reads the SKILL.md frontmatter into initial context and when the instructions match it reads the rest of the SKILL.md. Every LLM can do that.

If it's such a thing that every model already can support it and you don't need to do anything with it, why is it even a feature?

To be fair other providers have to implement reading a skill directory and only the frontmatter of the SKILL.md and read more of it when needed. But it's a LOT simpler than implementing MCP.