Hacker News Reader

robotoboson I still prefer MCP over skills

Haha sorry for the callout! Saw the M-dash and auto-assumed. Nice write up and thanks for sharing :)

robotoboson I still prefer MCP over skills

There's definitely some optimization that can occur, like an orchestrator or Ralph.

robotoboson I still prefer MCP over skills

Have not tried, but interesting. I guess my concern would be the Skill still takes up context space, where as MCP is just using CPU.

robotoboson I still prefer MCP over skills

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

robotoboson I still prefer MCP over skills

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.

robotoboson I still prefer MCP over skills

Despite thinking this is AI-generated, I agree but everything has a caveat.

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

MCP’s are great for custom, repeatable tasks. After 5-10 runs of watching my LLM write the same exact script, I just asked it to hardcode the solution and make it a tool. The result is runs are way faster and repeatable.