{"skill":{"slug":"universal-primitives","displayName":"Universal Primitives","summary":"通用执行器架构原理：大语言模型只需文件增删改查和执行脚本两个基元工具，配合其天然的文字理解能力，就能从\"无所不知只能输出文字\"跃迁到\"无所不能能控制任何软件硬件\"。当用户讨论AI能力边界、工具设计哲学、Agent架构原理、LLM与操作系统交互、如何让AI控制软件硬件等主题时触发。","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":110,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1776613036192,"updatedAt":1776613913485},"latestVersion":{"version":"1.0.0","createdAt":1776613036192,"changelog":"- Initial release of universal-primitives skill.\n- Explains the principle that LLMs need only file operations and command execution (\"two primitives\") to become general-purpose executors.\n- Details how these two primitives empower LLMs to create, modify, and run any software or control hardware indirectly.\n- Describes the minimal toolset philosophy and how Agent architectures reduce to combinations of these primitives.\n- Provides strategies for \"bootstrapping\" these primitives even in restricted Agent or user environments.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"wangjiaocheng","userId":"s175zq13kt63ypfry5rgxh1pv18440m2","displayName":"波动几何","image":"https://avatars.githubusercontent.com/u/25478397?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious","suspicious.vt_suspicious"],"summary":"Detected: suspicious.llm_suspicious, suspicious.vt_suspicious","engineVersion":"v2.4.0","updatedAt":1776613913485}}