Measuring the Marginal Utility of Skills at the Execution State

Skill libraries package procedural knowledge for agents, but retrieval ranks relevance rather than testing execution. We define the marginal utility $\Delta V(s_t,k)$ of a fixed package-plus-announcement protocol at execution state $s_t$ as its change in expected verified reward. At each checkpoint we replay one realised prefix, apply a protocol arm, independently continue it, and compare verifier rewards. Across 22 screened realised states from eleven SkillsBench tasks under one model and agent (516 runs), the health-gated own-package contrast was +0.147. Conditional on these fixed states, a runs-only 95% interval was [+0.082, +0.213] and within-state randomization gave $p<0.001$; an 11-cluster $t$ interval crossed zero [-0.020, +0.315] ($p=0.079$), making cross-task mean inference method-sensitive. Utility did not separate checkpoint rules, but uptake differed by +39.9 points between first-write-rule and three-fifths checkpoints; two no-write fallbacks and one reversed pair limit that label. Only two tasks had a foreign top-1. The contribution is a signed, state-conditioned protocol and auditable finite-sample map, not a router.