MetaSkill：用 DAG 让 Agent Skills 的组合编排可执行
Where Natural Language Ends in Agents: Executable Skill Composition with MetaSkill
Skills 之间怎么传递输出一直靠模型自己猜，这篇把依赖关系做成 DAG 直接可执行，做 Agent 编排的可以看看实现思路。
Agent Skills 用自然语言表达任务知识，但多个 Skill 组合时难以保证执行顺序和上游输出的传递。论文提出 MetaSkill，保留完整的 Skill 包与本地指令，同时把调用依赖和前置文本绑定转为可执行约束，通过有向无环图（DAG）运行时调度。在 20 个多 Skill 产物任务上，对比自然语言流程、Prompt Graph 和 AgentSkillOS，使用 DeepSeek-V4-Flash 和 GLM-5.2 两个模型。盲评显示 95% 任务自助法区间在部分对比中排除了平局，GLM-5.2 执行轨迹中所有计划节点完成且先后约束全部满足。代码已在 GitHub 开源。
Where Natural Language Ends in Agents: Executable Skill Composition with MetaSkill
Agent Skills express open-ended task knowledge in natural language, but composing them requires persistent execution order and upstream-output handoffs. We propose selective formalization at Skill boundaries: coordination relations with stable references and machine-checkable constraints become executable, while substantive task judgments remain within Skills. We introduce MetaSkill, a hybrid representation that preserves complete Skill packages and local instructions while making invocation dependencies and predecessor-text bindings executable through a directed acyclic graph (DAG) runtime. This interface supports explicit coordination without prescribing how each Skill performs its local task. Across 20 multi-Skill artifact tasks and two LLMs, we compare natural-language procedures, prompt-visible graphs, and MetaSkill derived from a common frozen plan per task, using the same designated Skill packages. Additional comparisons evaluate AgentSkillOS with the same available Skill packages as MetaSkill, as well as agent systems using their configured tools. Blinded artifact judgments yield favorable preference point estimates across all reported comparisons, with 95% task-bootstrap intervals excluding parity against Prompt Graph under DeepSeek-V4-Flash and OpenClaw under GLM-5.2. In audited GLM-5.2 execution traces, all planned nodes complete and all declared precedence constraints are satisfied. Together, these findings support MetaSkill as a practical interface for composing open-ended Skills, combining local linguistic flexibility with executable dependencies, explicit predecessor-text bindings, and auditable coordination. Code is available at: https://github.com/TokenRhythm/opensquilla/tree/paper/metaskill-lp4fm-2026
