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 zheng-xie-assessmentgit 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/zheng-xie-assessment)<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/zheng-xie-assessment"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/zheng-xie-assessment/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/zheng-xie-assessment"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/zheng-xie-assessment.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 | $0.00121 | $0.02667 |
| Opus 5 | $0.00060 | $0.01333 |
| Sonnet 5 | $0.00024 | $0.00533 |
| Haiku 4.5 | $0.00012 | $0.00267 |
Grade A, and why
zheng-xie-assessment 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zheng-Xie Assessment — 正邪虚实判断框架
R — 原文 (Reading)
正气存内,邪不可干。 — 《黄帝内经·素问》,刺法论篇第七十二
邪之所凑,其气必虚。 — 《黄帝内经·素问》,评热病论篇第三十三
邪气盛则实,精气夺则虚。 — 《黄帝内经·素问》,通评虚实论篇第二十八
I — 方法论骨架 (Interpretation)
面对任何问题,在动手解决之前,先做一次力量对比的定性判断: 是"自身力量不足"(虚),还是"外部压力过盛"(实)?
素问用"正"与"邪"这对概念来搭建这个分析框架: "正"是系统自身的能力、资源、抵抗力; "邪"是外部的压力、干扰、多余负担。 "虚"是正气不够——系统自身薄弱,需要补强; "实"是邪气过盛——外部压力太重,需要削减。
判断的依据是看问题发生在哪里:如果是"邪之所凑"(问题出现在防御薄弱处), 说明本质是虚——应该补;如果是外部压力明确过大导致系统不堪重负, 说明本质是实——应该泻。
虚实判断决定了完全相反的策略方向: 虚则补(增加资源、培训、投入),实则泻(削减压力、去除冗余、减轻负担)。 如果判断反了——虚的当实来泻(本来能力就不够还削减)或实的当虚来补 (本来负担就重还加码)——只会越治越糟。
现实中更多的情况是虚实夹杂:既有自身不足,又有外部过重。 这时需要攻补兼施——同时补正和泻邪,两手并用。
A1 — 书中的应用 (Past Application)
案例 1: 虚实判断与补泻策略
- 问题: 如何判断病情是虚还是实?该用补法还是泻法?
- 方法论的使用: 通评虚实论给出了明确定义:"邪气盛则实,精气夺则虚"。实是外部邪气过盛(如急性感染、淤堵),虚是内部精气不足(如慢性虚弱、免疫力低下)。判断准确后,实用泻法(汗、吐、下等祛邪手段),虚用补法(温、养、益等扶正手段)。
- 结论: 虚实判断是所有后续治疗决策的前提——判断错了方向,后面全错。
- 结果: 能准确辨别虚实的医生才能"万举万当",不能辨别的则会"虚虚实实"(虚的当实治、实的当虚治),反而加重病情。
案例 2: 正气存内的预防逻辑
- 问题: 面对疫病流行,为什么有些人感染有些人不感染?
- 方法论的使用: 刺法论用"正气存内,邪不可干"来解释:外部疫邪(环境压力)固然可怕,但如果自身正气充足,邪气就无法侵入。评热病论补充了反面:"邪之所凑,其气必虚"——凡是病邪能突破的地方,一定是因为那里本身薄弱。
- 结论: 预防的核心不是消灭所有外部威胁(不可能),而是确保自身正气充足——把薄弱环节加固。
- 结果: 正气充盛的人即使暴露于疫病环境中也不易感染,正气虚亏的人则首当其冲。
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 反复出现的低级错误: 团队/系统反复出现同样的问题,用户需要判断是该加强能力(补虚)还是该削减多余负担(泻实)。
- 资源分配的两难: 面对困境,不确定是该"投入更多资源"还是该"砍掉多余的东西"——方向完全相反,需要先做虚实判断。
- 精力耗尽却效果不佳: 用户感到已经非常努力但效果越来越差,需要判断是自身方法/能力不足(虚),还是承担了太多不必要的负担(实)。
语言信号 (用户的话里出现这些就应激活)
- "是该加强还是该精简?"
- "问题反复出现,到底怎么根治?"
- "已经很努力了但效果不好"
- "资源不够还是需求太多了?"
- "是能力问题还是压力问题?"
- "越用力越糟糕"
与相邻 skill 的区分
- 与
negative-feedback的区别: 正邪虚实是判断"虚(自身不足)还是实(外部过盛)"来决定策略方向,亢害承制是发现"某个力量过度亢盛"来引入制衡。前者是诊断型框架(判断虚实),后者是调控型框架(引入制约)。 - 与
cascade-prediction的区别: 正邪虚实聚焦于一个点的力量对比分析(够不够 vs 多不多),传变预测关注的是问题在不同点之间的传播路径。
E — 可执行步骤 (Execution)
当 skill 被激活后, agent 应按以下步骤执行:
- 评估正(自身力量)和邪(外部压力)
- 列出"正":系统的能力、资源、储备、韧性(如团队能力、资金储备、系统冗余度)。
- 列出"邪":外部压力、干扰、多余负担、有害因素(如不合理的需求、冗余流程、噪音干扰)。
- 完成标准: 产出"正邪清单",分别列出自身力量和外部压力的具体条目。
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 · 159 lines · 121 tokens per session scan A 7299706cf152
zheng-xie-assessment is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 121 tokens to every session and 2,667 once invoked, about $0.0006 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
article-magazine
Huashu / huashu-md-html-inspired magazine article layout for turning Markdown or notes into a polished long-form HTML essay.
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
card-twitter
Twitter quote or data card designed to pair with a post.
poster-hero
Vertical poster or Moments-style share image with strong visual impact.
deck-ljg-present
A presentation template that converts an outline or Markdown document into large, poster-like slides while keeping the original wording, order, and content. It uses black, red, or yellow colour themes and assigns document elements to slide layouts.