[et-al]

> Skills are good for instilling non-repeatable, yet intuitive or institutional knowledge.

Maybe I'm misinterpreting you, but can you explain this more? I've been using skills for repeatable tasks. Why an MCP instead?

[robotobos]

If the model can figure it out with tokens, but my institutional knowledge MCP tool can do it with a few CPU cycles, it’s faster and deterministic and repeatable.

[robotobos]

Saying "non-repeatable" was probably wrong. "Unique" might be better. Things LLMs arent naturally able to do or infer.