类经图翼·卷一·卷二「运气」（明·张介宾）研读

Community

dhicoc

从明·张介宾（张景岳）《类经图翼》卷一「运气上」、卷二「运气下」蒸馏出的运气学「图翼·象数基础」层框架——太极—阴阳—五行生成数—气数—五运（五天五运/五音建运太少相生/主客运）—六气（正化对化/主客气/司天在泉）—天符岁会—南北政脉不应，逐字照明本底本。用于「象数基础研读」与「图翼推算细节补足」，非临床指南。

Overview

Publisher	dhicoc
Repository	`wuyun-liuqi-skills`
Skill name	`类经图翼·卷一·卷二「运气」（明·张介宾）研读`
Stars	52
Forks	10
Bundled files	13
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
13 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by dhicoc on GitHub. Read the source before you install it.

Installation

Install the 类经图翼·卷一·卷二「运气」（明·张介宾）研读 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/dhicoc/wuyun-liuqi-skills/tree/master/rag-knowledge-base/distilled/liejing-tuyi-yunqi
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/dhicoc/wuyun-liuqi-skills/tree/master/rag-knowledge-base/distilled/liejing-tuyi-yunqi

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/dhicoc/wuyun-liuqi-skills.git /tmp/wuyun-liuqi-skills
mkdir -p .claude/skills
cp -r /tmp/wuyun-liuqi-skills/rag-knowledge-base/distilled/liejing-tuyi-yunqi .claude/skills/dhicoc

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 类经图翼·卷一·卷二「运气」（明·张介宾）研读 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads 类经图翼·卷一·卷二「运气」（明·张介宾）研读 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so 类经图翼·卷一·卷二「运气」（明·张介宾）研读 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

⚠️ 最高级安全警告（必读，贯穿本 skill 全部文件） 本 skill 仅用于中医运气学「图翼·象数基础」的文献研读与象数框架整理。书中含太极、阴阳、五行生成数、气数、五运六气推算等古代学术内容，严禁据此自行诊断、辨证、开方、推算剂量、判定体质或替代执业中医师。任何健康问题须咨询持证中医师；急症立即就医。本 skill 不提供任何医疗建议，所有古文均按明本底本逐字保留，仅作学术引证与历史文献研究。 禁止将本象数框架当作「按出生年/当前年自断运气、自取方、自疗」的依据。 取方、用量、加减、体质判断、临床处置均须由执业中医师面诊后决定。

核心框架与心智模型

本书是明·张介宾（张景岳）《类经图翼》卷一「运气上」、卷二「运气下」的象数基础整理。卷一立太极—阴阳—五行生成数—气数之象数地基（景岳自谓「医道开卷第一义」）；卷二以「图翼」（图解 + 图说）展开五运六气推算全框架（化运、五音建运太少相生、主客运、正化对化、主客气、司天在泉、天符岁会、南北政脉不应）。它与《运气诸方》（三因）、《运气证治歌诀》（王旭高）、《医宗金鉴·运气要诀》互补而非替代：

层级	书名	资产	侧重
图翼·象数基础层（本书）	类经图翼·卷一·卷二「运气」（张介宾）	asset37	太极—阴阳—五行生成数—气数哲学地基 + 图翼推算细节（五音建运、南北政脉不应等深度）
方源层	三因极一病证方论·卷五运气诸方（陈无择）	asset36	十六方药物组成、炮制分量、主治、煎服与随气加减（运气用方原方层）
歌诀层	运气证治歌诀（王旭高）	asset34	以歌诀体重述十干运方与六支气方、六淫治例（运气证治方歌层）
推算框架广度层	医宗金鉴·运气要诀（吴谦）	asset35	太极阴阳、五运六气推算、天符岁会、南北政体例广度（基本不载具体方剂）

四书互补（象数基础 → 方源 → 歌诀 → 框架广度），任何一书的研读都不可取代另外三书，更不可取代执业中医师面诊：

图翼·象数基础层（本书）：补全医宗金鉴所缺的太极—阴阳—五行—气数根基，并加五音建运、南北政脉不应等深度推算细节。
方源层（三因）：把运气格局落到十六个原方，提供「用方」的文献源流。
歌诀层（王旭高）：把同一套运气治法编成方歌，便于记诵与证治对照。
推算框架广度层（医宗金鉴）：提供「按年干支推算运气格局」的全框架广度。

本书灵魂（务必先读）

太极—阴阳本源（卷一·太极图论，逐字）：「太极本无极」，「太极动静而阴阳分」。
五行生成数（卷一·五行生成数解，逐字）：「天一生水，地六成之；地二生火，天七成之；天三生木，地八成之；地四生金，天九成之；天五生土，地十成之」；「太过者其数成，不及者其数生，土常以生也」。
气数平准（卷一·气数统论，逐字）：「至而至者和；至而不至，来气不及也；未至而至，来气有余也」。

章节索引（按需加载）

chapters/ch01-zonglun.md — 总论撮要 + 本书定位（图翼·象数基础层）+ 四书互补说明 + 张介宾运气观活法锚点（逐字引客气图解「不可胶柱」一句）
chapters/ch02-xiangshu-jichu.md — 卷一·运气上（象数·哲学地基）：太极图论 / 阴阳体象 / 五行生成数解 / 五行统论 / 气数统论
chapters/ch03-wuyun.md — 卷二·五运：五天五运 / 五音建运太少相生 / 主运图说 / 客运图说
chapters/ch04-liuqi.md — 卷二·六气：正化对化 / 主气六步 / 客气司天在泉 / 司天歌 / 推六气法 / 指掌法 + 灾变讨论（活法锚点）
chapters/ch05-tianfu-suihui.md — 天符 / 太乙天符 / 岁会 / 同天符 / 同岁会 / 六十年合计 28 年 / 天符岁会总歌 / 中执法中行令中贵人
chapters/ch06-nanbei-zheng.md — 南北政说 / 脉不应 / 阴阳交 / 尺寸反 / 南北政歌 / 推原南北政说
chapters/ch07-zuiqiang-jinggao.md — 🛑 最强警告章：禁止自行开方/剂量推算/体质诊断/替代就医
chapters/ch08-shiyong-zhinan.md — 取用指南：按年干支查运气格局、跨书取证、与 asset34/35/36 双轨/多轨衔接

主题索引（按需读章节）

想知道「运气总论 / 本书定位（象数基础层）/ 四书互补」 → chapters/ch01-zonglun.md
想知道「太极 / 阴阳 / 五行生成数 / 气数 / 干支五行」 → chapters/ch02-xiangshu-jichu.md
想知道「五天五运 / 五音建运太少相生 / 主客运 73 日零 5 刻」 → chapters/ch03-wuyun.md
想知道「正化对化 / 主气六步 / 客气司天在泉 / 司天歌 / 推六气 / 指掌法」 → chapters/ch04-liuqi.md
想知道「天符 / 太乙天符 / 岁会 / 同天符 / 同岁会 / 28 年统计」 → chapters/ch05-tianfu-suihui.md
想知道「南北政 / 脉不应 / 阴阳交 / 尺寸反」 → chapters/ch06-nanbei-zheng.md
想知道「安全红线最严口径」 → chapters/ch07-zuiqiang-jinggao.md
想知道「怎么按年份查格局 / 走 RAG 跨书取证」 → chapters/ch08-shiyong-zhinan.md

支撑文件

cheatsheet.md — 速查表（🛑 最高级警告置顶：五行生成数、干支五行、五天五运、五音太少相生链、主客运、正化对化、主气六步、司天歌、天符岁会统计、南北政口诀）
patterns.md — 可复用研读/推算模式（象数→推算衔接、图翼细节补足通用推算、四书多轨对照）
glossary.md — 术语（太极/阴阳/五行生成数/太过不及/平气/五天五运/五音建运/太少相生/正化对化/主气/客气/司天在泉/天符/岁会/太乙天符/同天符同岁会/南北政/脉不应/阴阳交/尺寸反/指掌法）
EVAL_vs_RAG.md — 单书象数框架 vs 跨书 RAG 取证对比（含 RAG 实跑验证）

📌 使用边界：本 skill 为「研读式」象数基础框架，不输出「你今年什么运、该用什么方、用多少量、是什么体质」之类个性化建议，更不提供任何处方。若需讨论具体用药或健康判断，请转正规中医师；本 skill 仅提供历史文献与方法论对照。

与 RAG 协作指引（何时用本 skill，何时调 rag_search）

本 skill 是《类经图翼》运气卷单书的深度象数基础框架；项目既有 RAG（scripts/rag_search.py）是跨 68 部文献的通用取证库。两者互补，非替代：

用本 skill（蒸馏框架）当：问题聚焦「这一本书」的象数根基 / 图翼推算细节 / 五音建运 / 南北政脉不应 —— 如「河图生成数怎么解」「甲己为何化土」「五音太少相生链」「南北政脉不应怎么定上下」「主客运各 73 日零 5 刻」。
调 rag_search.py（RAG）当：需要跨书原文出处、岁运病机现代化解读、临床医案佐证 —— 对应资产：
- asset1（岁运病机）、asset2（司天在泉）、asset4（方剂）、asset5（历代注家）、asset10（治法）、asset14（医案）。
最佳实践：先读本 skill 的象数框架（1 跳查表 cheatsheet.md / patterns.md），再用 rag_search --key 「liejing_key」 或 --asset 「资产」 补「原文出处 + 真实医案」。例如答「甲己为何化土」：本 skill 给五天五运图解与推原南北政说（ch03/ch06），RAG 拉出 asset5 历代注家与 asset1 岁运病机佐证。
统一入口（已注册 asset37）：本蒸馏已注册为 asset37_liejing_tuyi_yunqi，统一入口 key 为 liejing_*（如 liejing_xiangshu/liejing_wuyun/liejing_liuqi/liejing_tianfu/liejing_nanbei/liejing_zonglun），可直接 rag_search --key liejing_* 稳定命中（各 1 条，100% 精确键）；路由 routing id: liejing-tuyi-yunqi 已并入 routing.yaml，并与 asset34 / asset35 / asset36 同列 rag_search.py 默认检索范围。

全 skill 任何临床/剂量/诊断相关内容，均仅供文献研读，禁止据此自行用药，须咨询执业中医师。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the 类经图翼·卷一·卷二「运气」（明·张介宾）研读 AI skill do?

Why use 类经图翼·卷一·卷二「运气」（明·张介宾）研读 on TypingMind?

Because you install it once and use it with any model. 类经图翼·卷一·卷二「运气」（明·张介宾）研读 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install 类经图翼·卷一·卷二「运气」（明·张介宾）研读 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dhicoc/wuyun-liuqi-skills/tree/master/rag-knowledge-base/distilled/liejing-tuyi-yunqi. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use 类经图翼·卷一·卷二「运气」（明·张介宾）研读?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with 类经图翼·卷一·卷二「运气」（明·张介宾）研读?

As many as you like. As long as a model supports skills, you can use 类经图翼·卷一·卷二「运气」（明·张介宾）研读 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 类经图翼·卷一·卷二「运气」（明·张介宾）研读 AI skill free?

Yes. It is published on GitHub by dhicoc under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Ci Limits

openclaw

OrganizationPopular

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Openclaw Debugging

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

Openclaw Docker E2e Authoring

openclaw

OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

Openclaw Ghsa Maintainer

openclaw

OrganizationPopular

Inspect, patch, validate, publish, or confirm OpenClaw GHSA security advisories and private-fork state.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

核心框架与心智模型

本书灵魂（务必先读）

章节索引（按需加载）

主题索引（按需读章节）

支撑文件

与 RAG 协作指引（何时用本 skill，何时调 rag_search）

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now