I benchmarked my own agent skill, and today's Claude barely needed it

I wanted to write an agent skill that makes coding agents better at data analysis. The kind of mistakes I had in mind are the ones that produce a confident, wrong number: a "Total" row summed together with the countries, a join that duplicates orders, averaged p99s, timed-out requests that vanish from the latency percentiles, an A/B test that was... Weiterlesen: I benchmarked my own agent skill, and today's Claude barely needed it