thinking-framework

方源思维操作系统 - 基于《蛊真人》800万字小说深度蒸馏的AI Skill，7大心智模型+8条决策启发式

毛泽东思想 AI Skill —— 矛盾分析、实践论、实事求是等六大核心思维框架，含毛选静火版 1-7 卷全文

Cognitive memory that thinks — 7 laws, 3-tier memory, multi-agent. pip install soma-wisdom

Deconstruct problems via First Principles. Classify hidden assumptions (Fact/Norm/Belief/Interest) and rank the "Most Dangerous" using a Vulnerability×Impact matrix. Rebuild conclusions from verified premises. Best for major decisions, business validation & belief questioning. Triggers: axiom, first principles, deconstruct, underlying logic.

A meta-skill for AI agents: generate cognitive base skills from any thinking framework. Works with Claude Code, Codex, Gemini, Cursor, and any LLM agent.

Not just tidying up. A 6-stage pipeline that refines raw notes into knowledge-base-ready depth: structure, expand, self-audit, cross-reference existing entries, surface conflicts, and propose integration—with zero fabrication.

A cognitive base for AI agents — structural isomorphism detection across disciplines. 跨领域认知底座，让 AI 自动发现不同学科之间的结构同构。

徐扬生视角：伟大教育家与工程院院士的认知框架 ｜The Perspective of Yangsheng Xu: Claude Code Skill

叶天士 · 温病卫气营血辨证 skill（AI agent 角色技能包 / 中医思维蒸馏 / prompt persona）：把清代医家叶天士的辨证坐标系、六套框架、七条用药之禁与文人医家口吻，蒸馏为可调用能力。含《温热论》《临证指南医案》《叶氏医案存真》《叶选医衡》四部原著 10338 行正典、17 份维度分析、215 案医案库、158 条古今病名映射、20 组剂量卡、29 问 FAQ、校勘日志与可重跑核验脚本。引文逐字可核，不拟方、不诊断、不替代就医。温病派 · 病证条辨 · 读案教学 · 医学史 | Ye Tianshi TCM agent skill corpus · 卫气营血 · 中医知识库 · 经方派请用倪海厦 · 温病四大家之首 · 公版古籍数字化 · 不替代就医 · 医学教育

A cognitive base that makes AI agents reason from verified foundations instead of inherited conventions. 让 AI agent 从第一性原理出发推理，而不是继承惯例。

李白 · 诗仙思维Agent Skill（AI agent 角色技能包 / 人物思维蒸馏 / prompt persona）：把盛唐诗人李白的诗学观、创作六步法「气→象→体→夸→断→尽」、8 个心智模型、16 个意象母题、7 段式角色规则与口吻，蒸馏为可调用能力。含《李白诗全集》25 卷 1010 首 UTF-8 正典、14 维框架 12 份维度分析、58 篇名篇赏析、40 篇名篇导航、35 问 FAQ、编码损坏修复与校勘日志、31 个 Python 核验脚本。引诗一律 grep 可核，拟作必标非李白原作，涉酒涉丹涉暴力内置安全层与免责模板。唐诗鉴赏 · 出处考据 · 拟古写作 · 文学普及 | Li Bai Tang poetry agent skill corpus ·

Genius-level thinking engine for Claude Code — 9 frameworks, 81 mental models, 12 engines, TRIZ, Cynefin diagnosis

Professional LLM rules and frameworks that transform AI assistants into rigorous thinking partners with first-principles reasoning, assumption validation, and evidence-based analysis.

🏛️ Stop trusting one AI answer. A council of AI advisors that debate, peer-review anonymously, and deliver a verdict. Works with Claude, ChatGPT, Gemini & any LLM.

毛泽东skill：一个可运行的认知操作系统。基于6个维度（著作、对话、表达DNA、他者视角、决策记录、时间线）的深度调研，提炼了毛泽东的7个核心心智模型、10条决策启发式和完整的表达DNA。

Plugin framework for M5Stack I2C sensors: one binary auto-detects board family and bus topology across four hardware families. Threshold alarm engine, MQTT with Home Assistant discovery, REST API, and an on-device LLM router.

27 AI persona thinking-framework skills (Karpathy, Jobs, Naval, Taleb, 陆奇, 雷军...) + nuwa factory to distill new ones. Installable for Claude Code / Codex / OpenCode.

SPARK 认知重塑系统 — turn books you read into real thinking habits. Cognitive-science skill for Claude Code / Codex / OpenCode.