iterative-skill-refinement

jhhuh

Use when a skill exists but blind assessment shows it underperforms, or when iteratively improving a skill through experiment cycles while avoiding overfitting to fixed benchmarks

blind-skill-assessment

jhhuh

Use when comparing two versions of agent output to determine which is better, or when evaluating whether a skill produces higher quality results than baseline

experiment-set-design

jhhuh

Use when designing experiments to test whether a Claude Code skill is effective, or when planning how to validate a new or improved skill