robotobos
Re:I still prefer MCP over skills
on Friday April 10, 2026 @12:26PM (#47720472)
Haha sorry for the callout! Saw the M-dash and auto-assumed. Nice write up and thanks for sharing :)
Re:I still prefer MCP over skills
on Friday April 10, 2026 @12:25PM (#47720462)
There's definitely some optimization that can occur, like an orchestrator or Ralph.
Re:I still prefer MCP over skills
on Friday April 10, 2026 @12:24PM (#47720446)
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.
Re:I still prefer MCP over skills
on Friday April 10, 2026 @12:23PM (#47720435)
Saying "non-repeatable" was probably wrong. "Unique" might be better. Things LLMs arent naturally able to do or infer.
Re:I still prefer MCP over skills
on Thursday April 09, 2026 @11:24PM (#47713223)
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.
Re:I still prefer MCP over skills
on Thursday April 09, 2026 @10:15PM (#47712816)
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.