SkillECTOR: Adaptive Contextual Lean Skill Selector Framework

Reusable skills allow language-model agents to acquire specialized business or user-aligned behaviors and capabilities without modifying their underlying models. But, the real future of intelligent agents lies beyond just more skills; it lies in knowing exactly which skills to deploy, when, and why. While both language models and agent harnesses have become increasingly skill-aware, existing skill orchestrators remain mostly na\"ive and context-insensitive, with limited adaptation of retrieval breadth and ranking strategy to the task at hand. Such rigid orchestration will become progressively ineffective and inefficient (costly) as skill repositories expand, diversify, and accumulate overlapping capabilities. We present *SkillECTOR*, an evolving, adaptive, lean, and model-independent policy that learns how to construct a focused skill set for a given task/query as well as environment/user context with **0 LLM invocation** in its online inference path. Across multiple widely-used benchmarks ( s.a. SkillsBench, AgentSkillOS, and Dataverse) our framework significantly ($\delta \approx 12-17\%$) improves complete-skill coverage over LLM-based selectors. We observe significant improvement in task success ($\delta \approx 4-5\%$) with substantially lower token usage ($\approx 20-30$%) and lower inference latency ($\approx 25$%) when *SkillECTOR* is integrated with task agents (powered by advanced LLMs). Impacts become more pronounced as skill repositories grow larger. These findings establish adaptive skill orchestration as a compact control problem and offer a scalable yet more robust alternative to placing an additional language model before every agent task.