AI 技能库：从视频教程里自动提炼可执行技能
现在的 AI 智能体大多靠手写技能或文本指令，但网上有海量视频教程、文章、代码仓库等资源，它们包含的操作步骤和视觉信息没有被利用。这篇研究让 AI 能自动从这些多模态资源中提炼出可执行的技能，并组织成层级化的技能百科。比如看一个视频教程，AI 能提取出“先点哪里、再拖什么”的步骤，结合代码和文字说明，形成可复用的技能。在 7 个实际创作领域测试中，使用这种技能库的智能体平均得分比不用技能的高 11.9 个百分点。它不是你明天就能直接用的工具，但展示了让 AI 从人类示范中自主学习操作技能的新方向。
📄 原文摘要(英文)
Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand-written, text-centric, or derived from agent traces, leaving tutorial videos and other multimodal human resources largely underused. We present RESOURCE2SKILL, a framework that distills multimodal resources, including tutorial videos, repositories, articles, and reference artifacts, into executable skills for software agents. RESOURCE2SKILL organizes these skills as a hierarchical multimodal Skill Wiki, where each entry combines structured text, code, visual examples, metadata, and provenance. This design preserves complementary signals from different resources: videos capture temporal operations and visual effects, code captures executable tool patterns, and articles or artifacts provide conceptual and stylistic grounding. At inference time, agents retrieve and compose relevant skills from the wiki; when coverage is insufficient, the same construction operator can acquire new skills online. Across seven practical authoring domains, RESOURCE2SKILL improves average overall score by +11.9 percentage points over no-skill agents and outperforms strong harness baselines in 26 of 28 main-aggregate model-domain cells. Ablations confirm the value of multimodal skill format, hierarchical organization, source diversity, selection strategy, and online acquisition.