elvis@omarsar0 · XOpenClaw-Skill是一种为LLM智能体构建可复用技能库的方法。传统技能归纳通常将单条轨迹一次蒸馏成扁平的单次启发式规则，而OpenClaw-Skill通过搜索候选技能树来替代贪婪蒸馏，在迭代阶段中利用集体信号联合生成、识别和组合技能节点，最终输出结构化的技能树，旨在提升技能的多样性和泛化能力。论文详见arxiv。
// OpenClaw-Skill： Searching a Tree of Agent Skills //
If you build reusable skill libraries for your agents， this one is worth your time.
Equipping LLM agents with effective skills is most of the battle in real systems， and most skill-induction work distills one trajectory at a time into a flat pile of single-shot heuristics.
Searching a tree of candidate skills looks like a better way to get composition and coverage than greedy distillation.
OpenClaw-Skill uses a collective signal to jointly generate， identify， and compose skill nodes across two iterative phases. The output is a structured tree of skills built for diversity and generalization rather than a flat list.
Paper： https://arxiv.org/abs/2606.16774