What is negative-feedback?

A framework for spotting when a force or trend in a system has become excessive and needs a counterbalance. It treats limits and feedback as part of keeping a system healthy.

Reviewing overloaded goals, unchecked growth, rigid targets, or other overcorrections in teams, organizations, and systems, then identifying balancing measures.

It helps explain why pushing one goal too far can create new problems and shows where a corrective force may be needed.

negative-feedback — 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 negative-feedback

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/negative-feedback/github.svg)](https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/negative-feedback)

Your own site

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

Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,813 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	$0.00126	$0.02813
Opus 5	$0.00063	$0.01406
Sonnet 5	$0.00025	$0.00563
Haiku 4.5	$0.00013	$0.00281

Measured 12d ago against content hash 424006609863, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

negative-feedback 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/suwen/negative-feedback/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Negative Feedback — 亢害承制调控法

R — 原文 (Reading)

相火之下，水气承之；水位之下，土气承之；土位之下，风气承之；风位之下，金气承之；金位之下，火气承之；君火之下，阴精承之。帝曰：何也？岐伯曰：亢则害，承乃制，制则生化，外列盛衰，害则败乱，生化大病。

— 《黄帝内经·素问》，六微旨大论篇第六十八

I — 方法论骨架 (Interpretation)

任何力量如果不受制约地持续亢盛，最终会伤害系统本身——这就是"亢则害"。但自然界的健康系统中，每个亢盛的力量背后都跟着一个制约力量——这就是"承"。 "承乃制"——有了制约，系统才能保持动态平衡，维持正常的"生化"(运转发展)。如果制约机制缺失，系统就会走向"败乱"。

这个框架揭示了一个反直觉的道理：制约不是发展的阻碍，而是发展的前提。没有制约的亢盛不是"强大"，而是"正在走向崩溃的前兆"。

素问列举了六气之间的承制关系：火之下水承、水之下土承、土之下风承…… 每一对都是"亢盛力量→制约力量"的结构。这些承制关系是系统内置的负反馈环路——当A过度亢盛时， B就被激活来制约A，使系统回归平衡。

迁移到现代场景：严格的KPI(亢)需要配合创新指标(承)来制约；快速增长(亢)需要配合组织建设(承)来制约；强势领导(亢)需要配合 dissent 机制(承)来制约。关键是：承制机制要在亢盛之前就建好，而不是等亢盛出了问题再临时找。

A1 — 书中的应用 (Past Application)

案例 1: 六气的承制关系

问题: 为什么五运六气之中，每个主气之下都有一个"承"气？
方法论的使用: 素问逐一列出六气的承制配对：相火之下水气承之(水制火)，水位之下土气承之(土制水)，土位之下风气承之(木制土)……这不是随意搭配，而是按照五行相克的逻辑——每个力量都由"克它"的力量来制约。
结论: "亢则害承乃制制则生化"——有了承制，系统才能正常运转(生化)；失去承制，系统就会败乱。
结果: 理解承制关系的医生能判断"这个亢盛是正常的(有承制)还是危险的(失去承制)"，从而决定是否需要干预。

案例 2: 胜复循环的自动调节

问题: 当某个运气过度亢盛之后会发生什么？
方法论的使用: 至真要大论指出"有胜则复，无胜则否"——有过度亢盛(胜)就必定有反弹回复(复)，这是系统的自动调节机制。比如某年火气太盛(胜火)，随后就会有一股寒凉之气来回复平衡(复)。
结论: 胜复是自然的负反馈——过度的亢盛会自动唤起制约力量。但如果不等到自然回复就人为干预，或者更糟地继续推波助澜，就会破坏这个自动调节。
结果: 懂得胜复规律的医生在亢盛初起时不急于强力干预，而是顺势引导回复；不懂的医生可能在亢盛期继续助阳，加剧过冲。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

过冲现象: 系统中某个力量已经明显过度——指标飙高、行为极端、趋势过热——用户发现"越用力越糟糕"，需要引入制衡来纠偏。
设计自调节机制: 用户在构建一个新系统/组织/流程，需要提前内置制约机制，防止某个环节的亢盛失控。
单边推进后的反弹: 持续朝一个方向用力之后出现了反弹(团队倦怠、市场反噬、系统崩溃)，用户需要理解"为什么会这样"并设计承制。

语言信号 (用户的话里出现这些就应激活)

"越用力越糟糕"
"物极必反"
"用力过猛反而坏事"
"需要引入制衡/制约"
"这个趋势太猛了，会不会过热？"
"单方面推太远了，需要拉回来"
"系统缺乏自我调节机制"

与相邻 skill 的区分

与 zheng-xie-assessment 的区别: 亢害承制是发现"亢盛→引入制约"的调控动作，正邪虚实是判断"虚(不足)还是实(过盛)"的诊断动作。前者是"做了什么"，后者是"判断是什么"。两者经常串联使用：先用正邪虚实判断出"实(亢盛)"，再用亢害承制来"引入承制"。
与 cascade-prediction 的区别: 传变预测是"问题沿链条传播到下游"，亢害承制是"亢盛力量唤起制约力量"。前者是单向传播，后者是双向对抗。

E — 可执行步骤 (Execution)

当 skill 被激活后, agent 应按以下步骤执行:

识别哪个力量正在亢盛
- 观察系统中哪个指标、行为、趋势、力量正在持续走高、过度膨胀、失去节制。
- 判断亢盛的程度：是"正常范围内的旺盛"还是"已经超出平衡的亢盛"？
- 完成标准: 明确标注"亢盛力量是什么"以及"亢盛的具体表现"。

Read the full file on GitHub · 153 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 · 153 lines · 126 tokens per session scan A 424006609863

Subscribe to this mod's changes

negative-feedback is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 26d ago), licensed MIT. It adds 126 tokens to every session and 2,813 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.

Planning 公众号

negative-feedback