When your experiment isn't working and you're stuck running random variations hoping something sticks, this skill forces you into a structured 5-step diagnostic: collect failure cases, find a working baseline (even if you have to radically simplify), incrementally bridge the gap to isolate what breaks it, verify hypotheses with targeted experiments, then fix the actual cause. It's built around the idea that understanding why experiments fail matters more than running more of them. Comes with experiment logging templates that track purpose, setting, results, analysis, and critically, your own next steps. Works standalone or gets called from experiment-pipeline when a stage fails. The counterintuitive rules section is worth reading even if you don't use the whole flow.
npx skills add https://github.com/evoscientist/evoskills --skill experiment-craft