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 four-seas-regulationgit 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/four-seas-regulation)<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/four-seas-regulation"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/four-seas-regulation/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/four-seas-regulation"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/four-seas-regulation.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 | $0.00072 | $0.01627 |
| Opus 5 | $0.00036 | $0.00813 |
| Sonnet 5 | $0.00014 | $0.00325 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
four-seas-regulation 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
四海调节法: 核心枢纽管理
R — 原文 (Reading)
人有髓海, 有血海, 有气海, 有水谷之海, 凡此四者, 以应四海也。 气海有余则气满胸中悗息面赤, 气海不足则气少不足以言。 髓海有余则轻劲多力, 髓海不足则脑转耳鸣胫酸眩冒。 得顺者生, 得逆者败; 知调者利, 不知调者害。 审守其俞, 而调其虚实, 无犯其害。
— 黄帝/岐伯, 海论第三十三
I — 方法论骨架 (Interpretation)
四海调节法是一个通过管理系统的核心枢纽来调控整体的策略框架。
-
识别核心枢纽: 复杂系统有若干"海"——资源汇聚和分配的核心节点。灵枢识别了四个: 水谷之海(供应链/消化吸收)、血海(资源池/血液)、气海(动力源/呼吸动力)、髓海(指挥中心/神经中枢)。
-
每个海有输注点: 每个枢纽有入口(上输)和出口(下输), 管理就是"审守其输"——监控和管理这些进出口。
-
有余不足各有征兆: 每个海的状态会通过特定信号表现出来: 气海有余=气满胸闷, 不足=气短; 髓海有余=轻劲多力, 不足=头晕耳鸣。通过监测信号来判断各海的状态。
-
调其虚实不犯其害: 调节时不能伤害系统。方向正确则恢复("顺者得复"), 方向错误则败坏("逆者必败")。
A1 — 书中的应用 (Past Application)
案例 1: 髓海不足的诊断
- 问题: 一个人头晕耳鸣、腿酸无力、视力模糊、懈怠嗜睡, 是什么问题?
- 方法论的使用: 这些都是"髓海不足"的特征表现。髓海(脑)是全身的指挥中心, 髓海不足=指挥中心资源匮乏。
- 结论: 表面看起来是多个不相关的症状(头晕+耳鸣+腿酸+嗜睡), 实际上都指向同一个核心枢纽(髓海)的问题。
- 结果: 不需要逐个治疗每个症状, 只要调节髓海(通过其输注点), 所有症状都会改善。
案例 2: 气海的输注管理
- 问题: 如何管理气海(胸中宗气)?
- 方法论的使用: 气海的输注点: 上在柱骨之上下(颈部), 前在人迎(颈部动脉)。调节时通过这些输注点操作, "审守其俞而调其虚实"。
- 结论: 管理核心枢纽的关键是管理好它的输注点(进出口), 而不是直接操作枢纽本身。
- 结果: "无犯其害"——在输注点操作, 避免直接干预核心造成伤害。
A2 — 触发场景 (Future Trigger) ★
- 多点异常同因: 系统多个地方同时出问题, 可能是某个核心枢纽失调。
- 面面俱到失败: 试图管理所有细节但力不从心, 需要聚焦核心节点。
- 资源分配失衡: 某些区域资源过剩某些不足, 需要从枢纽层面调控分配。
语言信号
- "到处都有问题, 顾不过来"
- "有没有一个核心问题导致所有这些"
- "怎么用有限精力管理这么多事情"
- "需要抓住关键点"
E — 可执行步骤 (Execution)
-
识别系统的核心枢纽
- 列出系统中所有资源汇聚和分配的核心节点(供应链、资源池、动力源、指挥中心)。
- 完成标准: 识别出3-5个核心枢纽, 每个标注其功能和影响范围。
-
监测各枢纽状态
- 每个枢纽有哪些"有余"和"不足"的信号? 当前的信号指向什么状态?
- 完成标准: 每个枢纽标注当前状态(有余/不足/正常)和判断依据。
-
找到各枢纽的"输注点"
- 每个枢纽的关键进出口在哪里? 通过管理这些进出口来调节枢纽状态。
- 完成标准: 每个枢纽有至少1个可操作的输注点。
-
调节虚实的优先级
- 哪个枢纽的问题最紧急? 先调哪个? "无犯其害"——确保调节不会造成新问题。
- 完成标准: 给出调节顺序和每步的预期效果。
B — 边界 (Boundary) ★
不要在以下情况使用
- 简单系统: 只有一个中心的简单系统不需要四海框架, 直接管理即可。
- 枢纽间无关联: 如果各枢纽完全独立, 框架简化为逐一管理。
失败模式
- 忽略非枢纽问题: 不是所有问题都来自核心枢纽, 有时确实需要处理末端问题。
- 过度集中: 过于关注枢纽而忽视边缘问题, 导致"灯下黑"。
审计信息
- 验证通过: V1 ✓ / V2 ✓ / V3 ✓
- 测试通过率: {{%}} (详见 test-prompts.json)
- 蒸馏时间: {{DATE}}
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 · 115 lines · 72 tokens per session scan A 0542c9fb902b
four-seas-regulation is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 72 tokens to every session and 1,627 once invoked, about $0.0004 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.