SkillsInjector: Dynamic Skill Context Construction for LLM Agents

ArXi:2605.29794v1 Announce Type: new LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting skills does not always improve task completion and can even degrade it. Existing methods still treat skill injection as a static step, selecting skills with fixed criteria, fixing the budget in advance, and leaving descriptions unchanged. We argue that this static treatment can undermine the utility of skills, because which skills are exposed, how many are included, and how they are presented all affect downstream performance.