MetaGO Core Knowledge - 19 Meta-Thought Systems, 43 Fundamental Attributes, 36 Core Axioms, 13 Capability Families, 125 Engines, 984 Atoms, 927 Algorithms
Scanned 9/3/2026
Install to Claude Code
npx -y skills add metago-ai/metagolifeform --skill metago-core --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Metago Core?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/metago-ai-metago-core-64911363)More formats (shields.io, HTML) on the badges page.
---
name: metago-core
description: MetaGO Core Knowledge - 19 Meta-Thought Systems, 43 Fundamental Attributes, 36 Core Axioms, 13 Capability Families, 125 Engines, 984 Atoms, 927 Algorithms
---
# MetaGO 核心知识体系
元构全息智能引擎(MetaGO)V36.9.1 的核心知识库。当专家团成员需要查询元思想体系、根本属性、核心公理、能力族、引擎规格等元构知识时,按下列真实存在的文件获取(公开基线)。
## 参考资料(全部随仓库发布,实存可查)
- `AGENTS.md`(仓库根)— 运行法则母本 V36.9.1,17 章:8 公理、7 属性、四道决策锁、五阶段元进化、KMWI 四层记忆、14 类算法触发条件
- `core/METAGO_CORE.md` — 核心纲要:19 元思想体系、43 根本属性、36 核心公理、13 能力族总览
- `packages/engine/CONSTITUTION/AXIOMS.md` — 8 条关键公理完整条文(A6–A33 体系公理见蓝本,未发布)
- `packages/engine/CORE/ATTRIBUTES.md` — 43 条根本属性定义
- `packages/engine/CORE/PROTOCOLS.md` — 运行协议集
- `packages/engine/INDEX/knowledge.json` — 知识体系索引
- `packages/engine/INDEX/skills.json` — 97 技能索引
- `packages/engine/INDEX/engines.json` — 引擎规格索引(125 引擎 / 984 原子)
- `packages/engine/INDEX/tools.json` — 工具索引(57 工具 / 927 算法 / 14 触发类别)
- `skills/` — 97 个技能目录,含 19 元思想技能(metago-thought-01 ~ 19)的完整操作定义
## L3 完整蓝本说明
《元构全息智能引擎.txt》(34,655 行)未随公开仓库发布,按需向维护者索取。公开运行以上列文件为准——它们已自包含支撑全部 97 技能与引擎运行的知识,运行时无需读取蓝本。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...