Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
Linfeng Fan, Yuan Tian, Ziwei Li, Zhiwu Lu

TL;DR
This paper introduces extsc{SkillGuard}, a method for detecting and repairing skill drift in LLM agent libraries by extracting and validating environment contracts, significantly reducing false positives.
Contribution
It formulates skill drift as contract violation, proposes extsc{SkillGuard} for precise detection, and releases extsc{SkillDegrade}, a benchmark for skill degradation evaluation.
Findings
extsc{SkillGuard} achieves zero false alarms in no-drift cases.
In drift verification, extsc{SkillGuard} attains 100 ext{ extperthousand} precision and 76 ext{ extperthousand} recall.
Contract violations enable repair success rate to increase from 10 ext{ extperthousand} to 78 ext{ extperthousand}.
Abstract
LLM agents increasingly rely on reusable skill libraries, but these skills silently decay as the external services, packages, APIs, and configurations they reference evolve. Existing monitors detect such changes at the wrong granularity: they observe values, not the role those values play in a skill. A version string in a comment is noise; the same string in a pinned dependency is an operational obligation. We formulate skill drift as contract violation and introduce \sgname{}, which extracts executable environment contracts from skill documents and validates only those role-bearing assumptions against known or live conditions. This distinction turns noisy monitoring into a precision-first maintenance signal. Contract-free CI probes produce 40\% false positives, while \sgname{} raises zero false alarms over 599 no-drift and hard-negative cases (Wilson 95\% CI ). In…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
