SkillBridge: Cost-Aware Diagnosis and Repair of Cross-OS Compatibility Defects in Agent Skills
The paper addresses a practical failure mode for LLM agents: reusable executable skills that work on one operating system but break on another because OS assumptions are scattered across guide text, scripts, metadata, install contracts and local entrypoints. SkillBridge is a contract-based workflow with three stages — static analysis, dynamic validation and repair — that first screens 3,270 skill-target-OS cases covering 1,090 skills across Linux, macOS and Windows for OS-sensitive contract evidence, then runs dynamic tasks and root-cause review on selected cases. Repairing the contract field responsible for the failure raised the reviewer-judged target-task pass rate from 30.6% to 38.4%, a gain of 7.8 percentage points. A retrospective Linux/macOS budget analysis found SkillBridge reached 38 confirmed OS issues with 185 dynamic validations, versus roughly 865 validations expected under uniform random selection.