What is observation-inference?

A reasoning framework for estimating hidden conditions from several observable signals. It emphasizes comparing multiple clues instead of relying on one uncertain sign.

Assessing a person or system from indirect evidence, checking conflicting signals, and making cautious overall judgments.

It helps when the thing you want to assess cannot be measured directly or when visible clues disagree.

observation-inference — 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 observation-inference

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

Your own site

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

Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,500 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	$0.00145	$0.02500
Opus 5	$0.00072	$0.01250
Sonnet 5	$0.00029	$0.00500
Haiku 4.5	$0.00015	$0.00250

Measured 13d ago against content hash 1783fa7035fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

observation-inference 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/observation-inference/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

以外测内推理法 (Observation Inference)

R — 原文 (Reading)

切脉动静而视精明,察五色,观五脏有余不足,六腑强弱,形之盛衰,以此参伍,决死生之分。能合脉色,可以万全。得神者昌,失神者亡。

— 《素问·脉要精微论篇第十七》/《素问·五藏生成篇第十》/《素问·移精变气论篇第十三》

I — 方法论骨架 (Interpretation)

当无法直接观察内部状态时,可以通过多个外部信号来间接推断。素问的"参伍"法是核心: 不是依赖单一信号下结论,而是从多个维度收集外部信号(面色/眼睛/声音/体态/脉象), 然后交叉验证。关键原则有三:第一,信号必须有明确的内部对应关系(五色归五脏, 面色青→肝,赤→心,黄→脾,白→肺,黑→肾);第二,单一信号不可靠, 必须多信号交叉验证("参伍");第三,要区分真假信号——有些表面信号是假象 (如真寒假热),需要通过信号之间的矛盾来识别。这个方法论的本质是: 用多个间接测量(proxy measurement)的交叉验证来逼近直接测量的准确性。

A1 — 书中的应用 (Past Application)

案例 1: 四诊合参的综合判断

问题: 如何准确判断一个人的健康状况和预后
方法论的使用: 脉要精微论提出"切脉动静而视精明,察五色,观五脏有余不足,六腑强弱,形之盛衰,以此参伍"——同时收集脉象、眼神、面色、形体四个维度的信号,综合判断
结论: 单一维度可能误判(面色好但脉象差=假象),多维度交叉才能可靠
结果: 形成"能合脉色,可以万全"的判断原则

案例 2: 得神失神的预后判断

问题: 如何从外部信号判断一个人预后好坏
方法论的使用: 移精变气论提出"得神者昌,失神者亡"——从精神状态(反应灵敏度、眼神清亮程度、语言条理性)来判断内在生机。精神好=内部正气尚足,预后好;精神差=内部正气已衰,预后差
结论: 精神状态是最重要的外部信号之一,反映的是整体生命力的强弱
结果: 即使具体症状复杂,只要"得神"就说明核心机能还在,治疗空间大

案例 3: 五色生死判断

问题: 如何从面色判断病情轻重
方法论的使用: 五藏生成篇详细列出五色的生死判断:面色如草兹(枯暗青)、如枳实(暗黄)、如枯骨(惨白)等=死色;如翠羽(明润青)、如鸡冠(明润赤)等=生色。关键不在于颜色本身,而在于"明润"还是"枯暗"
结论: 面色的明润度反映内在气血是否充盈,枯暗则气血已败
结果: 形成了一套从面色明暗判断内在气血状态的视觉信号体系

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

需要评估某人的整体状态但无法做详细检测(如远程判断家人健康状况、面试中评估候选人状态)
多个外部信号互相矛盾,需要综合判断真实情况(如一个人说没事但面色和语气都很差)
需要从有限的外部线索推断系统内部状态(如从产品外观和用户反馈推断内部质量,从团队表面和谐推断深层问题)
需要建立一套外部观察→内部推断的信号体系

语言信号 (用户的话里出现这些就应激活)

"从表面怎么看出来内在状态"
"几个信号互相矛盾,该信哪个"
"怎么在不做检查的情况下判断情况"
"他说没事,但我总觉得不对"
"有没有办法从外部判断内部情况"
"表面看起来挺好的,但总觉得有问题"

与相邻 skill 的区分

与 emotion-organ-proxy 的区别: 情志脏腑模型是从情绪(主观心理信号)推断脏腑状态,以外测内是从客观外部信号(面色/声音/体态/脉象)推断内部状态。两者都是间接推断,但信号性质不同。
与 five-flavors-balance 的区别: 五味调和是从饮食偏好这个特定维度分析脏腑状态,以外测内是从多个外部信号的交叉验证来综合判断。前者是单一维度的深入分析,后者是多维度的广度判断。

E — 可执行步骤 (Execution)

当 skill 被激活后, agent 应按以下步骤执行:

收集多维度外部信号
- 完成标准: 已从至少三个不同维度收集可观察的外部信号(如面色/精神/声音/体态/行为模式等)。判停条件:若只能获取单一维度的信号,应明确告知单一信号的局限性,不建议下确定结论
建立信号与内部状态的映射
- 完成标准: 已将每个外部信号映射到可能的内部状态(如面色暗→气血不足,声音低微→气虚,反应迟钝→"失神"),形成"信号→内部状态"的对应表

Read the full file on GitHub · 141 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 · 141 lines · 145 tokens per session scan A 1783fa7035fb

Subscribe to this mod's changes

observation-inference is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 145 tokens to every session and 2,500 once invoked, about $0.0007 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.

Research proxy 公众号

observation-inference