Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add dhicoc/wuyun-liuqi-skills --skill five-elements-networkgit clone --depth 1 https://github.com/dhicoc/wuyun-liuqi-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/five-elements-network)<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/five-elements-network"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/five-elements-network/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/five-elements-network"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/five-elements-network.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.02955 |
| Opus 5 | $0.00050 | $0.01477 |
| Sonnet 5 | $0.00020 | $0.00591 |
| Haiku 4.5 | $0.00010 | $0.00296 |
Grade A, and why
five-elements-network scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
五行生克网络思维
R — 原文 (Reading)
五行者, 金木水火土也。更贵更贱, 以知死生, 以决成败, 而定五脏之气, 间甚之时, 死生之期也。 五脏受气于其所生, 传之于其所胜, 气舍于其所生, 死于其所不胜。 五脏相通, 移皆有次。五脏有病, 则各传其所胜。
— 岐伯, 藏气法时论篇第二十二、玉机真藏论篇第十九
I — 方法论骨架 (Interpretation)
五行生克网络思维是一套用于分析多要素系统中连锁效应的结构化方法。
其核心逻辑分为四层:
-
要素归五行: 将系统中的关键要素归入五类。每一类有其属性和功能。归类的标准不是表面相似, 而是功能角色——谁是生长的力量(木)、谁是驱动的力量(火)、谁是承载转化的力量(土)、谁是收敛规范的力量(金)、谁是蕴藏滋养的力量(水)。
-
画生克关系图: 五行之间存在两种基本关系——"生"(滋养、促进)和"克"(制约、抑制)。相生链条: 木生火、火生土、土生金、金生水、水生木, 构成正向循环。相克链条: 木克土、土克水、水克火、火克金、金克木, 构成制衡循环。
-
沿链条推导: 某一行的变化会沿相生链向下传导(母病及子), 也会沿相克链产生压力(乘——过度克制, 或侮——反克)。因此, 局部的变化可以推导出全局的连锁效应。
-
找到关键干预点: 连锁效应意味着"治一处牵全局"。干预的关键不是直接作用于症状所在的行, 而是找到链条上的关键节点——生链条上游(补母)或克链条的对立面。
这个框架的独特价值在于: 它把"事物相互影响"的模糊认知变成了一套可操作的关系图+推导规则。
A1 — 书中的应用 (Past Application)
案例 1: 怒伤肝的连锁传导
- 问题: 一个人长期愤怒(怒属木/肝), 除了肝脏本身, 还会影响什么?
- 方法论的使用: 将"怒"归入木(肝)。沿相克链推导: 木克土, 肝气郁结会"乘脾"(过度克制脾/土), 导致消化问题——食欲不振、腹胀。沿相生链推导: 木生火, 肝气不舒可化火扰心, 出现失眠、心悸。
- 结论: 一个情绪问题(怒)不只是局部问题, 会沿生克网络传导到消化(土)和心血管(火)两个子系统。
- 结果: 治疗不能只治肝, 还要兼顾健脾(防木乘土)和清心(防木火扰心)。这就是"五脏相通, 移皆有次"的临床含义。
案例 2: 五脏传变预测
- 问题: 肝脏有病, 接下来会如何发展?
- 方法论的使用: "五脏受气于其所生, 传之于其所胜"——肝(木)受气于肾(水, 所生/母), 传之于脾(土, 所胜)。沿链条推导: 肝病→传脾(消化受影响)→若不治→继续传肾→最终至肺(金, 木所不胜之脏)而死。
- 结论: 疾病不是静态的, 而是沿着五行生克链条有序传变。预测传变路径可以提前阻断。
- 结果: "治未病"的具体操作之一——在疾病沿生克链条传到下一个脏腑之前, 先加固那个脏腑, 阻断传变。
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 局部问题引发全局反应: 某个部门/子系统出了问题, 用户担心会连锁影响其他部门/子系统, 需要预测传导路径。
- 多要素交织的复杂问题: 问题涉及5个左右的关键要素, 且要素之间存在支持(生)和制约(克)关系, 线性因果分析不够用。
- 反复出现的循环问题: 问题此起彼伏, 解决A又冒出B, 说明底层有一个循环机制在驱动, 需要画出关系图才能看清。
语言信号 (用户的话里出现这些就应激活)
- "动了A, B和C都跟着变了"
- "这个问题总是牵扯到好几个方面"
- "解决了这个, 那个又冒出来了"
- "它们之间好像有某种连锁反应"
- "只治局部不管用, 一停就复发"
与相邻 skill 的区分
- 与
yin-yang-balance的区别: 阴阳平衡处理两个对立面的关系(二分法), 五行生克处理五个(或多个)要素的网络关系(多维互动)。要素多于两个时优先用五行。 - 与
biao-ben-priority的区别: 标本缓急决定优先级(先做什么), 五行生克揭示传导路径(做了之后会怎样传导)。
E — 可执行步骤 (Execution)
当 skill 被激活后, agent 应按以下步骤执行:
- 要素归五行: 将关键要素分类
- 列出系统中所有相关要素(目标5个左右), 根据其功能角色归入五行分类: 生长/启动(木)、驱动/活跃(火)、承载/转化(土)、收敛/规范(金)、蕴藏/滋养(水)。
- 完成标准: 每个要素都已归入一个类别, 且归类理由清晰(不是随意贴标签)。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 149 lines · 100 tokens per session scan A 3c2e9742a274
five-elements-network is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 100 tokens to every session and 2,955 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
论文图表助手
A diagram-making assistant for flowcharts, system architecture diagrams, sequence diagrams, class diagrams, and mind maps. It can create standalone browser files that export diagrams as PNG images.
external-gitcode-ascend-arxiv-recommendation-npu
A research pipeline for finding recommended papers on arXiv, an online archive of scientific research papers, and checking whether they include source code.
external-mindstudio-ascend-profiler-db-explorer
A skill that turns questions about Ascend PyTorch Profiler and msprof database files into SQL queries. These files record profiling information such as operator time, communication, dispatch, and scheduling.
edu-analytic-geometry
An interactive teaching webpage that solves an analytic-geometry problem, with the question, step-by-step formulas, and a live 2D diagram. It can take written questions, generate random ones, or read a question from an uploaded image.
education-advanced-quantitative-modeling
Use when education research needs advanced quantitative modeling beyond common t-tests, ANOVA, chi-square, correlation, and simple regression. Covers multilevel/hierarchical linear models, SEM, latent variable models, mediation, moderation, moderated mediation, IRT, longitudinal/growth models, DID, propensity score…
lc_arxiv
A tool for searching arXiv, a public repository of research papers, mainly in science and technology.