It still surprises me how effective the /simplify skill is.
I’ve also had some great results with a /reflect skill that asks the agent to look at the work in the broader context of the project. But those are the only two skills I use regularly that aren’t specific to our company, codebase, or tools.
Some engineers I work with have had less than desirable results with /simplify but it overall seems to work! I used to use some of the humanlayer subagents but they haven't been updated in several months
Do you really think a random person off the street knows more about how LLMs work internally than the latest frontier model (that has been trained on that material)?
No, but a random person off the street also isn't making skills for LLMs.
I think that LLMs are trained on the millions of vibe written LLM blog posts that are more superstition than fact. There is a lot of snake oil out there that is treated as fact. If someone claims that an LLM is better than humans at something I always want to see the rigorous evaluations that have been done to quantify it, not "but they're trained on everything!"
Hmmm, I disagree. The AI is exceedingly average at everything it does and requires an expert human-in-the-loop to catch things that appear plausible but are slop. To that degree I think there is a difference between "AI generated" and slop.
My money's on that.