Packaging the safety policy as a modular skill-native artifact provides substantial gains over flattening the identical policy into a system prompt: SkillSonar reduces ID ASR from 0.353 to 0.104 and OOD ASR from 0.437 to 0.109, increases ID task utility from 0.655 to 0.815, and lowers token consumption from ~239K to ~188K (a ~21% reduction).

Packaging the safety policy as a modular skill-native artifact provides substantial gains over flattening the identical policy into a system prompt: SkillSonar reduces ID ASR from 0.353 to 0.104 and OOD ASR from 0.437 to 0.109, increases ID task utility from 0.655 to 0.815, and lowers token consumption from ~239K to ~188K (a ~21% reduction). · CiteArk

Measurement results

0/12 assessed

0 supported0 disputed or conflicting12 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
split: id_test · configuration: Flattened prompt	0.353 fraction	—	Not assessed
split: ood_test · configuration: Flattened prompt	0.437 fraction	—	Not assessed
split: id_test · configuration: SkillSonar	0.104 fraction	—	Not assessed
split: ood_test · configuration: SkillSonar	0.109 fraction	—	Not assessed
split: id_test · configuration: Flattened prompt	0.655 score	—	Not assessed
split: ood_test · configuration: Flattened prompt	0.672 score	—	Not assessed
split: id_test · configuration: SkillSonar	0.815 score	—	Not assessed
split: ood_test · configuration: SkillSonar	0.789 score	—	Not assessed
configuration: Flattened prompt	0.748 score	—	Not assessed
configuration: SkillSonar	0.763 score	—	Not assessed
configuration: Flattened prompt	239 thousands_of_tokens	—	Not assessed
configuration: SkillSonar	188 thousands_of_tokens	—	Not assessed

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results