What is qi-regulation?

A framework for restoring a system’s underlying function instead of only treating its visible symptoms. It separates the outward problem from the condition causing it.

Use it to investigate recurring failures, poor team or process performance, and other functional problems. It is for choosing interventions aimed at restoring normal operation.

It helps when repeated surface fixes do not solve the problem. The approach asks whether something is missing, excessive, stuck, or interfering, then checks whether the system improves.

qi-regulation — Skill for Claude Code by dhicoc

Install

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.

Any agent

npx skills add dhicoc/wuyun-liuqi-skills --skill qi-regulation

Clone the repo

git clone --depth 1 https://github.com/dhicoc/wuyun-liuqi-skills

Made for: Claude Code.

Or install wuyun-liuqi-skills, the plugin that ships this one along with the rest of its 38 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/qi-regulation/github.svg)](https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/qi-regulation)

Your own site

<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/qi-regulation"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/qi-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/qi-regulation"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/qi-regulation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,219 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00097	$0.02219
Opus 5	$0.00048	$0.01110
Sonnet 5	$0.00019	$0.00444
Haiku 4.5	$0.00010	$0.00222

Measured 12d ago against content hash 0d049a6ed4f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

qi-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.

scripts/lib/neijing_snapshot/lingshu/qi-regulation/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

调气治本框架

R — 原文 (Reading)

用针之类, 在于调气。气积于胃, 以通营卫, 各行其道。凡用针者, 虚则实之, 满则泄之, 宛陈则除之, 邪胜则虚之。气至而有效, 效之信, 若风之吹云, 明乎若见苍天。

— 黄帝/岐伯, 九针十二原第一、刺节真邪第七十五

I — 方法论骨架 (Interpretation)

调气治本框架是一个从"处理表面症状"转向"恢复系统功能状态"的元方法论。

其核心操作分为四层:

识形气: 区分"形"(表面表现/结果)和"气"(功能状态/原因)。症状是形, 导致症状的功能失调是气。头痛是形, 气血不通是气; 团队效率低是形, 沟通通道阻塞是气。
调气而非治形: 干预的目标不是消除表面现象, 而是恢复系统的正常运行功能。"用针之类在于调气"——一切手段都服务于恢复功能状态这个根本目标。
四个方向: 虚则补(增益不足), 实则泻(祛除多余), 宛陈则除(疏通淤滞), 邪盛则祛(排除干扰)。先判断属于哪种情况, 再选方向。
有效的验证标准: "气至而有效"——系统产生积极反应是干预有效的标志。效果应该是可感知、可验证的, "若风之吹云"般清晰。

这个框架的威力在于: 将注意力从"问题表现"转移到"系统功能", 从"消灭症状"转移到"恢复秩序"。

A1 — 书中的应用 (Past Application)

案例 1: 久病不愈的根因

问题: 久病是否不可治?
方法论的使用: 岐伯用四个比喻回答——"刺虽久犹可拔也, 污虽久犹可雪也, 结虽久犹可解也, 闭虽久犹可决也"。关键不是病了多久, 而是方法对不对。"疾虽久犹可毕也, 言不可治者未得其术也。"
结论: 问题拖得久不代表不能解决, 而是之前的干预一直在治形(处理表面), 没有调气(恢复功能)。
结果: 找到正确的功能恢复路径, 久病也能治愈。

案例 2: 经脉不通的解结法

问题: 一条经脉上实下虚, 气血不通, 如何处理?
方法论的使用: "此必有横络盛加于大经, 令之不通"——先找到阻塞原因(横络压迫), 然后"视而泻之, 此所谓解结也"——在阻塞点精准疏通。
结论: 不是整条经脉都有问题, 而是某个点阻塞导致全线不通。调气就是找到并疏通这个关键阻塞点。
结果: 阻塞疏通后, 气血自然恢复流通, "营卫之行上下相贯如环之无端"。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

反复处理表面问题无效: 用户一直在"灭火"但问题反复出现, 需要从"治形"转向"调气"。
系统功能失调: 某个系统(团队/身体/流程)的核心功能不正常, 直接干预无效, 需要恢复其运行状态。
长期问题久拖不决: 问题存在很长时间, 多种方法都试过但无效, 需要"治本"思维。

语言信号 (用户的话里出现这些就应激活)

"这个问题反复出现, 怎么也解决不了"
"一直在救火, 从来没有从根本上解决"
"各种方法都试过了还是不行"
"感觉系统本身出了问题, 不只是某个环节"

与相邻 skill 的区分

与 excess-deficiency-decision 的区别: 调气治本是元原则(干预的目标是恢复功能), 虚实补泻是操作方向(具体该怎么补或泻)。先确定"要调气", 再用虚实补泻决定"怎么调"。
与 bottleneck-unblock 的区别: 调气治本是思维方式(关注功能而非形式), 解结通滞是具体方法(找阻塞点疏通)。调气是"为什么要这样做", 解结是"具体怎么做"。

E — 可执行步骤 (Execution)

当 skill 被激活后, agent 应按以下步骤执行:

区分形与气: 识别表面现象与功能失调
- 列出当前所有的"形"(可观察到的异常表现/症状), 然后追问每个"形"背后的"气"(是什么功能失调导致了这个表现)。
- 完成标准: 每个"形"都找到了对应的"气", 且"气"是功能性描述而非现象重复。
判断属于四种情况中的哪一种
- 虚(功能不足→需要增益) / 实(功能亢盛→需要抑制) / 瘀(功能阻塞→需要疏通) / 邪(外部干扰→需要排除)。
- 完成标准: 明确给出判断并说明依据。
- 判停条件: 如果多种情况并存, 标记为"混合型", 分别处理。

Read the full file on GitHub · 139 lines

Changes

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 · 139 lines · 97 tokens per session scan A 0d049a6ed4f6

Subscribe to this mod's changes

qi-regulation is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 97 tokens to every session and 2,219 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.

Debugging 公众号

qi-regulation