Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that describe workflows, tools, resources, and domain conventions. While convenient for inspection and reuse, this design requires the same reusable procedure to be repeatedly injected into the runtime context. We propose Skill-to-LoRA(S2L), a behavior-centric skill representation that replaces runtime skill text with skill-specific LoRA adapters. Rather than compressing the skill document itself, S2L models the behavioral change induced by the skill text: offline, the complete SKILL.md is used to synthesize skill-guided demonstrations; online, the full document is omitted and the corresponding LoRA adapter is dynamically loaded to activate the learned skill behavior. We evaluate S2L with Qwen3.6-27B on a 21-skill subset of SWE-Skills-Bench. Compared with the no-skill and Full Skill Text baselines, S2L improves pass rate by 2.9 and 5.2 percentage points, respectively, while reducing per-step token cost by 6.6% relative to Full Skill Text prompting. S2L matches or improves Full Skill Text on 18/21 skills and the no-skill baseline on 15/21 skills. Control experiments further show that the gains depend on skill-specific adapter alignment: Wrong-LoRA and Shared-LoRA both reduce performance. These results suggest that many procedural agent skills can be converted from runtime instructions into trainable, dynamically loadable behavioral modules. Code will be released upon acceptance.

翻译：智能体技能通常以SKILL.md文件形式分发：这些人类可读的规程文档描述了工作流、工具、资源和领域约定。虽然便于检查和复用，但这种设计需要将相同的可复用规程反复注入运行时上下文。我们提出Skill-to-LoRA（S2L），一种以行为为中心的技能表示方法，用技能特定的LoRA适配器替代运行时技能文本。S2L并非压缩技能文档本身，而是建模技能文本引发的行为变化：离线阶段，完整的SKILL.md被用于合成技能引导的演示样本；在线阶段，完整文档被省略，转而动态加载对应的LoRA适配器以激活习得的技能行为。我们在SWE-Skills-Bench的21个技能子集上，使用Qwen3.6-27B评估了S2L。与无技能基线及完整技能文本基线相比，S2L的通过率分别提升2.9和5.2个百分点，同时相比完整技能文本提示，每步token成本降低6.6%。在21个技能中，S2L在18个任务上匹配或超越完整技能文本，在15个任务上超越无技能基线。控制实验进一步表明，性能提升依赖于技能特定的适配器对齐：错误LoRA与共享LoRA均导致性能下降。这些结果表明，许多规程性智能体技能可从运行时指令转化为可训练、可动态加载的行为模块。代码将在论文接收后开源。