What is cascade-prediction?

A method for predicting how a problem in one part of a connected system may spread to other parts. It is based on a traditional Chinese medicine model in which illness moves through organs along set paths.

Use it to map propagation paths, assess chain reactions, and decide where to add safeguards in systems such as software, organizations, or supply chains.

It helps identify likely downstream effects before a local problem becomes a wider failure.

cascade-prediction — 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 cascade-prediction

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

Your own site

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

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,367 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	$0.00104	$0.02367
Opus 5	$0.00052	$0.01184
Sonnet 5	$0.00021	$0.00473
Haiku 4.5	$0.00010	$0.00237

Measured 13d ago against content hash 934825165e46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cascade-prediction 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 13d 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/cascade-prediction/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cascade Prediction — 脏腑传变预测法

R — 原文 (Reading)

五脏受气于其所生，传之于其所胜，气舍于其所生，死于其所不胜。病之且死，必先传行，至其所不胜，病乃死。 ……五脏相通，移皆有次。五脏有病，则各传其所胜。

— 《黄帝内经·素问》，玉机真藏论篇第十九

I — 方法论骨架 (Interpretation)

系统中的问题不会停留在原地——它会沿着固定的路径向外传播。素问用五脏相克的链条来描述这个传播路径：肝(木)→脾(土)→肾(水)→心(火)→肺(金)→肝(木)，每个环节的问题都会传给"它所克"的下一个环节。

这个方法论的核心价值在于：问题不是随机扩散的，而是有方向、有次序的。掌握了传播路径，就可以提前预判下一个受害的环节，在那里预先布防。

它包含三个关键操作：第一，定位——当前问题出在哪个环节；第二，画路径——按相克链推出问题的传播方向和顺序；第三，设防——不等问题传到下一个环节，提前在那里加固。

这个思路迁移到任何有"环节A出问题会影响环节B"的系统都适用—— 组织管理、供应链、技术架构、生态链条，只要能画出"谁影响谁"的传递路径，就能用传变预测来防患于未然。

A1 — 书中的应用 (Past Application)

案例 1: 五脏传变路径与时间预测

问题: 五脏之病不治，会如何传变？何时会危及生命？
方法论的使用: 素问给出了完整的传变路径：肝受气于心(木生火)→传之于脾(木克土)→气舍于肾(水生木)→至肺而死(金克木)。心、脾、肺、肾各有类似的链条。并且给出了传变的时间预估："法三月，若六月，若三日，若六日"。
结论: 传变有固定方向(所胜)和终点(所不胜)，预判了路径就可以在中间环节阻断。
结果: 能预判疾病走向的医生("上工")可以在传变途中拦截，不能预判的("下工")只能被动应付。

案例 2: 外痹内传五脏

问题: 风寒湿引起的痹症(外感)如何影响内脏？
方法论的使用: 痹论指出：骨痹不已→内舍于肾，筋痹不已→内舍于肝，脉痹不已→内舍于心……外部的病邪沿着特定的对应关系逐步深入内脏。
结论: 外部问题如果持续不解决，会按固定路径向深层传播——从功能层(筋骨脉肌皮)传到核心层(五脏)。
结果: 提示必须在痹症尚在外层时就积极治疗，防止内传。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

局部问题需评估全局影响: 某个部门/模块/组件出了问题，用户需要预测这个问题会沿着什么路径扩散，最终影响哪些环节。
预防性布防: 用户知道某处出了问题，想在问题扩散之前提前加固下游环节，而不是等问题传到再仓促应对。
复盘连锁故障: 系统已经发生了连锁崩溃，用户需要回溯问题的传播路径，理解为什么A坏了最终导致Z也坏了。

语言信号 (用户的话里出现这些就应激活)

"这个问题会不会引发其他问题？"
"如果不处理会怎样？"
"一处出问题，其他地方会不会跟着出事？"
"需要提前在哪里布防？"
"连锁反应/多米诺效应"
"这个问题会扩散到什么范围？"

与相邻 skill 的区分

与 context-adaptation 的区别: 传变预测关注的是问题在时间维度上的扩散路径(下一步会怎样)，因地制宜关注的是问题在空间维度上的环境适配(换个地方怎么办)。前者是纵向预测，后者是横向适配。
与 negative-feedback 的区别: 传变预测是"问题沿着链条传播"，亢害承制是"某个力量过度亢盛需要引入制衡"。前者是线性传播，后者是过冲-回调。

E — 可执行步骤 (Execution)

当 skill 被激活后, agent 应按以下步骤执行:

定位当前问题所在的环节
- 将系统拆解为若干环节/模块/部门，确定问题当前出在哪一个环节。
- 完成标准: 明确标注"当前问题位置"以及该环节的核心功能。
画出传变路径图(相克链)
- 梳理系统中各环节之间的"谁影响谁"关系，画出传递链条。
- 从当前问题环节出发，沿传递方向逐级推导：问题会传到哪个环节？再下一个是哪个？
- 标记每个环节的"承受能力"：哪些环节脆弱(容易传变)，哪些环节有缓冲(可能阻断传播)。
- 完成标准: 产出一幅传变路径图，标注每一步的传播方向和预计影响时间。
- 判停条件: 若系统各环节完全独立无传递关系，则不存在传变路径，此 skill 不适用。

Read the full file on GitHub · 148 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.

13d ago First seen · 148 lines · 104 tokens per session scan A 934825165e46

Subscribe to this mod's changes

cascade-prediction is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 104 tokens to every session and 2,367 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.

Planning 公众号

cascade-prediction