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 yin-yang-balancegit 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/yin-yang-balance)<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/yin-yang-balance"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/yin-yang-balance/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/yin-yang-balance"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/yin-yang-balance.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 | $0.00092 | $0.02486 |
| Opus 5 | $0.00046 | $0.01243 |
| Sonnet 5 | $0.00018 | $0.00497 |
| Haiku 4.5 | $0.00009 | $0.00249 |
Grade A, and why
yin-yang-balance 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
阴阳平衡分析框架
R — 原文 (Reading)
黄帝曰: 阴阳者, 天地之道也, 万物之纲纪, 变化之父母, 生杀之本始, 神明之府也。 阴胜则阳病, 阳胜则阴病。阳胜则热, 阴胜则寒。 阴平阳秘, 精神乃治; 阴阳离决, 精气乃绝。
— 黄帝/岐伯, 阴阳应象大论篇第五、生气通天论篇第三
I — 方法论骨架 (Interpretation)
阴阳平衡分析法是一个用于诊断和纠正系统失衡的结构化框架。
其核心操作分为三层:
-
归阴阳: 将任何现象归入阴阳两个对立面。阳代表主动、温热、外向、兴奋; 阴代表被动、寒凉、内敛、抑制。这不是贴标签, 而是建立一种"用对立面看问题"的视角。
-
判盛虚: 判断哪一方过盛、哪一方不足。"阳胜则热, 阴胜则寒"——失衡必然表现为某一方的症状。关键是区分"某一方过盛"还是"另一方不足", 因为纠正方向完全不同。
-
用对立面纠正: 阳盛则补阴抑阳, 阴盛则补阳抑阴。纠正的方向永远是向对立面借力, 而不是直接压制过盛方。
-
平衡态是目标: "阴平阳秘, 精神乃治"——系统恢复平衡时, 功能自然正常。平衡不是静态的50/50, 而是动态的相互制约。
这个框架的威力在于: 任何复杂系统, 只要能归阴阳, 就能用同一套逻辑分析。
A1 — 书中的应用 (Past Application)
案例 1: 阳盛则热的病理表现
- 问题: 某人出现发热、口渴、面红等亢奋症状, 如何理解其本质?
- 方法论的使用: 将症状归阴阳——热、亢奋、外向均属阳, 判定为"阳胜"。根据"阳胜则热, 阳胜则阴病", 阳气过盛不仅产生热象, 还会消耗阴液(津液受损)。
- 结论: 表面是"热", 实质是阴阳失衡——阳过盛而阴受损。
- 结果: 治疗方向不是单纯降温, 而是"热者寒之"的同时兼顾养阴, 防止阳盛伤阴导致"阴阳离决"。
案例 2: 阴阳匀平的平人标准
- 问题: 如何定义健康状态?
- 方法论的使用: 用阴阳平衡标准定义健康——"阴阳匀平, 以充其形, 九候若一, 命曰平人"。
- 结论: 健康不是"没有病", 而是阴阳处于动态平衡, 充养形体, 脉象调和。
- 结果: 这一标准将"平衡"从抽象概念变为可操作的诊断标准——通过脉象(九候)是否调和来判断阴阳是否平衡。
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 系统失衡分析: 用户描述某个系统出现"一方过强一方过弱"的矛盾, 如团队中"推的人太多拉的人不够", 或身体"上火但手脚冰凉"。
- 对立冲突诊断: 问题是两股相反力量在对抗——热与冷、快与慢、兴奋与抑制、扩张与收缩——需要判断谁盛谁虚。
- 纠正方向迷茫: 用户知道某个方面出了问题, 但不确定该"加强弱的"还是"压制强的", 需要找到正确的干预方向。
语言信号 (用户的话里出现这些就应激活)
- "一边X一边Y, 感觉很不平衡"
- "总是太X, 缺少Y"
- "怎么判断是该补还是该泄"
- "系统在两个极端之间摇摆"
- "过度的X导致了Y的问题"
与相邻 skill 的区分
- 与
five-elements-network的区别: 阴阳平衡处理两极对立关系(一对矛盾), 五行生克处理多要素网络关系(五个要素的连锁)。问题只有两个对立面时用阴阳, 有三个以上要素相互影响时用五行。 - 与
biao-ben-priority的区别: 阴阳平衡解决"方向"问题(该补还是该泄), 标本缓急解决"顺序"问题(先治哪个后治哪个)。
E — 可执行步骤 (Execution)
当 skill 被激活后, agent 应按以下步骤执行:
-
归阴阳: 将现象归入对立面
- 列出当前系统中所有异常表现, 将每一项归入"阳面"(主动/温热/外向/亢奋)或"阴面"(被动/寒凉/内敛/抑制)。
- 完成标准: 所有异常表现已归入阴阳两列, 且两列的定义一致(不混用不同维度的阴阳)。
-
判盛虚: 判断失衡方向
- 统计阴阳两列的症状数量和严重程度, 判断是"某方过盛"还是"某方不足"。
- 完成标准: 明确给出判断——"X盛Y虚"或"X虚导致Y相对偏盛", 并说明判断依据。
- 判停条件: 若症状全部归入一面, 无法形成对立, 则跳到步骤3, 建议用户补充对立面的信息。
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 · 142 lines · 92 tokens per session scan A 1464c36241e7
yin-yang-balance is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 92 tokens to every session and 2,486 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.