Context Adaptation

Community

dhicoc

context-adaptation

用户需要在新的环境/市场/文化中部署已有方案时;当同一个问题在不同地区/场景下表现不同时; 当需要将通用方案本地化时;当用户说"为什么在这里不管用"或"换个地方方案就失效了"时。不适用于: 环境因素不重要、问题与场景无关的纯技术/逻辑场景。

Overview

Publisher	dhicoc
Repository	`wuyun-liuqi-skills`
Skill name	`context-adaptation`
Stars	52
Forks	10
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by dhicoc on GitHub. Read the source before you install it.

Installation

Install the Context Adaptation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/dhicoc/wuyun-liuqi-skills/tree/master/scripts/lib/neijing_snapshot/suwen/context-adaptation
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/dhicoc/wuyun-liuqi-skills/tree/master/scripts/lib/neijing_snapshot/suwen/context-adaptation

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/dhicoc/wuyun-liuqi-skills.git /tmp/wuyun-liuqi-skills
mkdir -p .claude/skills
cp -r /tmp/wuyun-liuqi-skills/scripts/lib/neijing_snapshot/suwen/context-adaptation .claude/skills/context-adaptation

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Context Adaptation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Context Adaptation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Context Adaptation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Context Adaptation — 因地制宜思维

R — 原文 (Reading)

医之治病也，一病而治各不同，皆愈何也？岐伯对曰：地势使然也。 ……故圣人杂合以治，各得其所宜，故治所以异而病皆愈者，得病之情，知治之大体也。

— 《黄帝内经·素问》，异法方宜论篇第十二

I — 方法论骨架 (Interpretation)

同一个问题在不同环境中会呈现不同的面貌，因此不存在放之四海皆准的单一方案。素问用五方(东、西、北、南、中)的体质差异和治疗差异来阐明这个原理：东方人易生痈疡宜砭石，西方人体质刚强宜毒药，北方人脏寒宜灸焫，南方人挛痹宜微针，中央人痿厥宜导引按蹻——同样的"治病"，五个地方五种打法。

关键不在于记住五种方案，而在于掌握"因地"的思维方式：先分析当前环境的特征(气候、饮食、体质、风俗)，再判断这些特征对方案的影响，最后选择适配的方案或将多种方案"杂合"使用。

当你的方案在新环境中失效时，问题通常不在方案本身，而在于你假设了一个"标准环境"——但真实环境永远有地方性。 "杂合以治"进一步提醒：当单一方案不够时，可以组合多个方案，让每种手段各发挥其适宜的部分，不必执着于唯一解。

A1 — 书中的应用 (Past Application)

案例 1: 五方异治

问题: 同样是治病，为什么东方用砭石、西方用毒药、北方用灸焫、南方用微针、中央用导引按蹻？
方法论的使用: 素问逐一分析五方的地理气候→饮食习俗→体质特征→好发疾病，再给出对应的最佳治法。东方海滨多鱼盐，人多热中痈疡，故宜砭石排脓；北方天寒地冻，人脏寒满病，故宜灸焫温阳。
结论: 治法的差异不是随意的，而是由环境决定的。"地势使然也"——地势不同，方案必须不同。
结果: 五种治法各自在本地区效果最优，但"杂合以治"的高手可以综合运用，"各得其所宜"。

案例 2: 西北与东南的体质差异与治法调整

问题: 同样的病，在西北和东南要用不同的治法。
方法论的使用: 五常政大论指出"西北之气散而寒之，东南之气收而温之，所谓同病异治也"。西北阴精奉上，人体质偏实，需要散邪；东南阳精降下，人体质偏虚，需要固守。
结论: "同病异治"——诊断相同但环境不同，方案必须调整。
结果: 因地施治的患者恢复更快，而照搬方案的疗效不佳。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

方案迁移失效: 用户有一个在A地/A场景/A市场验证成功的方案，迁移到B地/B场景后发现效果大打折扣，需要诊断原因并调整。
多地并行部署: 用户需要同时在多个不同地区或场景下推行同一个项目/产品/政策，需要因地制宜地设计变体。
本地化改造: 用户的通用方案需要适配特定文化、气候、法规或用户习惯，不能原样照搬。

语言信号 (用户的话里出现这些就应激活)

"为什么在这里管用在那里就不管用了？"
"换个地方方案就失效了"
"能不能直接复制那个方案过来？"
"每个地区的情况不一样"
"需要做本地化适配"
"一刀切的方案不行"

与相邻 skill 的区分

与 cascade-prediction 的区别: 因地制宜关注的是"同一问题在不同环境下的适配"，传变预测关注的是"一个问题如何连锁扩散到其他环节"。前者是空间维度，后者是时间维度。
与 zheng-xie-assessment 的区别: 因地制宜是分析环境特征来调整方案，正邪虚实是评估自身能力vs外部压力来决定补还是泻。前者聚焦环境差异，后者聚焦力量对比。

E — 可执行步骤 (Execution)

当 skill 被激活后, agent 应按以下步骤执行:

分析当前环境特征
- 列出目标环境的关键特征: 地理/气候条件、文化/习俗、用户特征、制度/规则约束。
- 与原方案的假设环境做对比，标记差异点。
- 完成标准: 产出一份"环境差异清单"，至少列出3个显著差异。
对照方案-环境匹配表
- 将原方案的每个关键要素逐一与目标环境对照，判断是匹配、冲突还是缺失。
- 特别关注: 哪些要素在新环境中会失效？哪些要素反而更有价值？哪些新要素需要补充？
- 完成标准: 对每个关键要素标注"保留/调整/替换/新增"。
- 判停条件: 若所有要素均匹配无冲突，则说明环境差异不大，可跳到步骤3简化调整。
调整方案或杂合多个方案
- 对"调整"和"替换"的要素，设计适配新环境的替代方案。
- 若单一方案不足以覆盖，采用"杂合以治"——组合多种方案的精华，让每种手段各得其所宜。
- 完成标准: 产出本地化的最终方案，并标注每处调整对应的环境原因。

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

环境因素不重要的纯逻辑问题: 如数学计算、代码语法等，答案与地域/场景无关的场景，因地制宜无意义。
已有精确量化模型的场景: 如果环境变量已经被数学模型精确捕获(如工程标准件设计)，不需要用定性分析替代。

作者在书中警告的失败模式

不明地势就施治——素问明确说"必明天道地理，阴阳更胜……乃可以知人之形气"，不分析环境就套方案是"妄行"。
执着于单一方案——"杂合以治"才是最高境界，如果固守一种治法排斥其他方法，就无法"各得其所宜"。

作者的盲点 / 时代局限

素问的地域分类(五方)过于粗略，现代社会的环境差异远比东西南北复杂——需要增加维度(行业、组织文化、技术栈等)。
古代的"因地制宜"主要靠经验积累，现代可以借助数据分析做更精确的环境-方案匹配。

容易混淆的邻近方法论

"具体问题具体分析"——因地制宜不是笼统的"看情况"，而是有一套结构化的环境特征→方案适配的分析流程。
"A/B测试"——A/B测试是事后验证哪个方案更好，因地制宜是事前根据环境特征预判哪个方案更合适，两者互补。

审计信息

验证通过: V1 ✓ / V2 ✓ / V3 ✓
测试通过率: {{%}} (详见 test-prompts.json)
蒸馏时间: 2026-04-18

Frequently asked questions

What does the Context Adaptation AI skill do?

Why use Context Adaptation on TypingMind?

Because you install it once and use it with any model. Context Adaptation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Context Adaptation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dhicoc/wuyun-liuqi-skills/tree/master/scripts/lib/neijing_snapshot/suwen/context-adaptation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Context Adaptation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Context Adaptation?

As many as you like. As long as a model supports skills, you can use Context Adaptation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Context Adaptation AI skill free?

Yes. It is published on GitHub by dhicoc under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Cuda Index Width

pytorch

OrganizationPopular

Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64_t, canUse32BitIndexMath, CUDA_KERNEL_LOOP_TYPE, or…

Plan Change

Turn a feature request into a minimal, file-level implementation plan before any code.

Simplified English

Write user-facing comments, plans, and documents in ASD-STE100 Simplified Technical English — short, unambiguous sentences with approved words and one meaning each — so readers understand them the…

Archify Review

Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.

Context Adaptation

Overview