What is five-flavors-balance?

A traditional Chinese medicine approach to balancing the five basic tastes—sour, bitter, sweet, pungent, and salty—in food.

Use it when planning food combinations, discussing strong taste preferences, or asking about diet-based ways to adjust bodily states.

It provides a framework for discussing how eating too much of one taste or adjusting tastes to a reported condition may affect health.

five-flavors-balance — 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 five-flavors-balance

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/five-flavors-balance/github.svg)](https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/five-flavors-balance)

Your own site

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

Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,507 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	$0.00134	$0.02507
Opus 5	$0.00067	$0.01254
Sonnet 5	$0.00027	$0.00501
Haiku 4.5	$0.00013	$0.00251

Measured 12d ago against content hash 9813ace4157f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

five-flavors-balance 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/five-flavors-balance/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

五味调和原则 (Five Flavors Balance)

R — 原文 (Reading)

谨和五味,骨正筋柔,气血以流,腠理以密,如是则骨气以精。谨道如法,长有天命。阴之所生,本在五味;阴之五宫,伤在五味。是故多食咸则脉凝泣而变色,多食苦则皮槁而毛拔,多食辛则筋急而爪枯,多食酸则肉胝皱而唇揭,多食甘则骨痛而发落。

— 《素问·生气通天论篇第三》/《素问·五藏生成篇第十》

I — 方法论骨架 (Interpretation)

饮食不是简单的"吃饱吃好",而是一门精确的调配术。食物有五种基本味道——酸、苦、甘、辛、咸, 每种味道各有归入的脏腑:酸入肝、苦入心、甘入脾、辛入肺、咸入肾。适量则滋养对应脏腑, 过量则伤害该脏腑乃至其所克之脏。调和五味的关键不是"都吃一点"这种均摊法, 而是根据自身脏腑的虚实状态来增减:某脏偏虚则适当多食对应之味以补之, 某脏偏盛则减少对应之味以防过亢。同时要注意"五味所伤"——任何一味长期过量都有明确的病理后果。这是一套以味觉为媒介的脏腑调节系统。

A1 — 书中的应用 (Past Application)

案例 1: 五味过量的具体伤害

问题: 偏食某一味会有什么后果
方法论的使用: 素问逐一列举五味过量的伤害:多食咸→脉凝泣变色(伤血/心);多食苦→皮槁毛拔(伤肺);多食辛→筋急爪枯(伤肝);多食酸→肉胝皱唇揭(伤脾);多食甘→骨痛发落(伤肾)
结论: 每种味道过量都有明确的脏腑伤害路径,味道偏好不是小事
结果: 形成一套"五味→五伤"的对应体系,作为饮食警示

案例 2: 脏腑苦欲补泻的食疗方案

问题: 特定脏腑出了问题应该吃什么味的食物
方法论的使用: 藏气法时论给出"苦欲补泻"原则:肝苦急食甘以缓之,心苦缓食酸以收之,脾苦湿食苦以燥之,肺苦气上逆食苦以泄之,肾苦燥食辛以润之
结论: 不是简单地"缺什么味补什么味",而是要根据脏腑的具体病态(急/缓/湿/逆/燥)来选择对应之味
结果: 将饮食调节从笼统的"均衡"推进到精确的"对症调味"

案例 3: 压力大嗜甜的现象解释

问题: 为什么有些人压力大时特别想吃甜食
方法论的使用: 思虑过度伤脾(土),脾欲甘——身体本能地通过甜味来补脾。但多食甘则骨痛发落(甘入脾,土克水,过甘伤肾)
结论: 嗜甜是身体自救的本能信号,但长期依赖甜食反而会伤害肾(骨骼和头发)
结果: 解释了"用甜食减压→越吃越虚"的恶性循环机制

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

发现自己长期偏好某一种味道(如无辣不欢、嗜甜、极咸),想了解可能的健康影响
需要制定日常饮食方案,希望从中医角度理解五味搭配
出现某些身体症状,想知道是否与饮食偏好有关(如皮肤干燥与嗜苦、掉头发与嗜甜)
想通过日常饮食调理某个脏腑(如肝不好该多吃什么味)

语言信号 (用户的话里出现这些就应激活)

"我最近特别想吃XX味的食物"
"饮食上怎么搭配比较健康"
"我口味偏重/偏甜/偏辣,有没有问题"
"XX脏腑不好,吃什么能调理"
"总觉得吃什么都不香,味觉有点麻木"

与相邻 skill 的区分

与 seasonal-regimen 的区别: 四时调养是按季节全面调度起居运动情志,五味调和是按味道偏好调节饮食对脏腑的影响。两者在饮食维度有交集,但切入点不同——前者以季节为纲,后者以味道为纲。
与 emotion-organ-proxy 的区别: 情志脏腑模型是从情绪推断脏腑状态,五味调和是从饮食味道推断脏腑状态。两者都是脏腑分析的不同入口,但信号来源完全不同。

E — 可执行步骤 (Execution)

当 skill 被激活后, agent 应按以下步骤执行:

评估当前五味摄入的偏向
- 完成标准: 已识别用户饮食中哪些味道偏多、哪些偏少,形成"五味摄入偏向图"(酸/苦/甘/辛/咸各占多少)
对照五味归脏表找到影响
- 完成标准: 已将每种偏多/偏少的味道映射到对应脏腑(酸→肝、苦→心、甘→脾、辛→肺、咸→肾),并指出偏多之味可能造成的伤害(如咸多→脉凝泣,甘多→骨痛发落)
调整到均衡并给出具体方案
- 完成标准: 已给出减少偏多之味、适当补充偏少之味的具体饮食建议,且方案考虑了用户的具体脏腑状态(有虚则补、有盛则减)。判停条件:若用户已有明确的脏腑诊断,直接跳到对症调味步骤

Read the full file on GitHub · 135 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 · 135 lines · 134 tokens per session scan A 9813ace4157f

Subscribe to this mod's changes

five-flavors-balance is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 134 tokens to every session and 2,507 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.

公众号

five-flavors-balance