Back to AI News
arxiv

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.

AI Brief

It offers a concrete, cost-aware method and measured results for a real portability problem teams hit when reusing agent skills across operating systems.

arXiv:2611.26256v1 Announce Type: cross Abstract: LLM agents increasingly reuse executable capabilities through skills, but a skill that works on one OS may fail on another because OS assumptions are spread across guide text, scripts, metadata, install contracts, and local entrypoints. Diagnosing such failures by running every skill on every OS is expensive: many executions spend model tokens, runner time, and review effort before revealing whether the failure is truly OS-related. We present SkillBridge, a contract-based workflow with three stages: static analysis, dynamic validation, and repair. SkillBridge first screens 3,270 skill-target-OS cases, covering 1,090 skills across Linux, macOS, and Windows, to find OS-sensitive contract evidence. It then runs dynamic tasks and root-cause review on selected cases to confirm whether a failure is caused by an OS assumption, and repairs the contract field that caused the failure, such as guide text, package scripts, dependencies, or platform declarations. Repair raises 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 further shows the efficiency effect: SkillBridge reaches 38 confirmed OS issues with 185 dynamic validations, where uniform random selection would require about 865 validations in expectation.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!