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.
npx skills add dhicoc/wuyun-liuqi-skills --skill context-adaptationgit clone --depth 1 https://github.com/dhicoc/wuyun-liuqi-skillsWrote 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.
[](https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/context-adaptation)<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/context-adaptation"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/context-adaptation/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.
<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/context-adaptation"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/context-adaptation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.02263 |
| Opus 5 | $0.00047 | $0.01131 |
| Sonnet 5 | $0.00019 | $0.00453 |
| Haiku 4.5 | $0.00009 | $0.00226 |
Grade A, and why
context-adaptation 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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。
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 · 142 lines · 94 tokens per session scan A cee3edea026b
context-adaptation is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 94 tokens to every session and 2,263 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.
Other skills, from other repositories
en-zh-translation-polish
An English-to-Chinese translation and editing process focused on natural Chinese rather than word-for-word wording.
en-zh-max
An English-to-Chinese translation and polishing guide. It produces natural Chinese translations, and can also provide English and Chinese text side by side.
中文文档写作
A set of templates and formatting rules for writing Chinese technical documents. It covers READMEs, design documents, development logs, and explanatory text.
cultural-dislocation-detector
A detector for systematic misunderstandings that arise when ideas from one culture are interpreted through another culture’s familiar assumptions. It checks whether a translation or explanation preserves the original question behind a concept.
zh-doc-translate
A set of instructions for translating technical documents between Chinese and English while preserving code blocks, formatting, commands, links, and selected technical terms.
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.