Common Skill Creator

Do not skip the baseline. The standard requires a with-skill versus without-skill comparison for new skills, and pressure hardening requires evidence rather than intuition.

Even a “simple” skill needs intent capture, activation description, implementation rules, baseline and with-skill runs, comparison of assertions/tokens/time, and iteration on observed failures. For discipline skills, record rationalizations, red flags, stop conditions, and behavior assertions in evals.

If time is constrained, reduce the test set; do not turn an unmeasured draft into a completed skill. “It is simple,” “the baseline is obvious,” and “the wording is self-evident” are red flags: stop, snapshot where applicable, run baseline, then continue from measured evidence.