Sansi Erhouxing logo

Sansi Erhouxing

Community
Job-Yang
sansi-erhouxing

三思而后行:改任何已成形的文档之前(写文章、改稿、调研、方案、技能文档),先通读全文骨架再动手,别只盯一段、别补丁摞补丁。这是前置动作技能,跟写作/改稿技能并行、先于它们跑,不是二选一:它管「动手前先看整体」,写作类技能管「怎么写好」,两层都走,先三思再动笔,别因带了"润色""精简"就跳过。最典型、命中必用:改文档、补一段或一节、精简/润色/优化/压缩/扩写已有段落、新增章节、按评审意见改稿。触发词:改文档、改稿、补内容、加一节、改一处、改一段、顺手改、只改这一处、润色、精简、优化、通篇优化、整篇改、压缩、扩写、顺一顺、通篇顺一顺、调措辞、重写这节、评审意见、反馈意见。DO NOT USE WHEN:从零新起一篇、纯一句话答疑、代码/工程改动(交给专门的验证流程)。

Overview

PublisherJob-Yang
Repositoryjobyang-ai-skills
Skill namesansi-erhouxing
Stars
100
Forks
5
Bundled files
3
LicenseMIT
Links
  • 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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Job-Yang on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Job-Yang/jobyang-ai-skills/tree/main/skills/sansi-erhouxing
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/Job-Yang/jobyang-ai-skills.git /tmp/jobyang-ai-skills
mkdir -p .claude/skills
cp -r /tmp/jobyang-ai-skills/skills/sansi-erhouxing .claude/skills/sansi-erhouxing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sansi Erhouxing 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 Sansi Erhouxing 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 Sansi Erhouxing 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.

三思而后行 · 改前通读的自律流程

改任何已成形的文档之前,先看整体,再动手。软约束,不阻断交付,只挡在「要动手改」这个动作前面。

范围说明:本技能只管文档类产物(文章、调研、方案、技能文档等成形文字)的修改。代码/工程改动不在本技能范围,交给专门的验证流程,别在这里处理。


为什么单开这个技能

不替你写,只挡在修改动作前面。

文档、方案、技能文档这类成形的东西,都会犯同一个毛病:只盯局部,不看整体。这个毛病不属于任何一个具体产物,单开一个技能来管它。

它是前置动作,跟写作/改稿技能并行,不是二选一。 那些技能管怎么把内容写好,这个技能管的是动手之前先看整体骨架——判断这处怎么改才不破坏整体。它是底层能力,该跟具体的写作技能一起走,不占它们的名额。顺序是:先三思(看骨架、判断这处怎么改才不破坏整体),再动手写/改。别因为一句话里带了"润色""精简",就只想着动笔、把这一步跳了。


触发场景(反模式清单)

命中任一即启动:

  • 评审 / 反馈意见指出文档某处有问题,准备直接冲上去改那一处,没回头看全文。
  • 用户说「改一下」「加一段」「顺手改一下」「只改这一处」「补一下」「快速改一下」。
  • 用户说「润色一下」「精简一下」「优化下措辞」「压缩这段」「扩写一下」「顺一顺」——文字加工也是改已有内容,先看这段在骨架里的位置再动。
  • 用户丢一整篇文章说「优化一下」「通篇顺一顺」,没指改哪儿——别逐句润色,先抽骨架,自己找出承接断了、论据放错节、结论收不全的地方(细则见 doc-scope.md)。
  • 新增一段内容 / 一节章节,准备挂在已有文档末尾。
  • 改文档的一节,没重读其他章节。
  • 处理别人对文档的评审意见,准备逐条改,不看全文骨架。
  • 迭代 / 更新一个已有技能文档、方案、配置说明。

不触发:从零新起一篇(没有既有骨架可通读)、纯一句话答疑、明确说"随手写个一次性草稿"。


「整体」怎么定义(按载体分)

不同载体,「整体」落到不同东西上:

载体「整体」指什么通读到什么程度
文档 · 修改一处全文骨架 + 前后章节的承启知道这一处在骨架里的位置、上一段收在哪、下一段起在哪
文档 · 通篇优化(没指改哪儿)全文骨架 + 论据归位 + 结论闭合抽出主干,自己找出哪几节承接断了、论据放错了、结论收不全(细则见 doc-scope.md)
文档 · 新增一节全文骨架 + 主线新节能不能顺进骨架,顺不进去要么调骨架,要么不加(细则见 doc-scope.md)
技能文档更新SKILL.md 主体 + 所有 references + 已发布版本 frontmatter找到本次改动的既有依据,不叠加平行防线;不覆盖已定的 description
方案/配置说明完整方案/配置文件 + 上游被谁引用改一处能说出谁会受影响

三步硬约束(改前必走)

底子是三条业界经典:Shotgun Surgery(改一处要连带看多处)、Chesterton's Fence(拆之前先搞清它为什么在)、Outline-First(骨架先立)。源头见 references/prior-art.md。

通读整体

按上表读到位。不到位不许下笔。

  • 文档:通读全文,列出骨架(一节一句话观点)。
  • 技能文档:读 SKILL.md 主体 + 所有 references。
  • 方案:读完整方案。

列影响面

两栏,写下来(重档)或口头说清(中轻档):

  • 这次要动的点:准备改/新增的具体位置。
  • 跟这个点相关的既有逻辑:文档骨架里的前后章、已有的类似论述、依赖此处的下游章节。

相关的没列全,不许下笔。

三问过闸

一条一条问,一条不过就停:

  1. 这个点,全文 / 技能历史 / 方案版本里之前动过吗? 动过就先看历史,别把上次刚删的加回来,别推翻上一次评审已经定的事(对应 Chesterton's Fence)。
  2. 修法的风险比原问题大吗? 大就换修法,别硬扛(对应 Band-Aid 反模式)。
  3. 改这一处,会不会破坏整体骨架的连贯? 破坏就回骨架重来,不许硬插(对应 Shotgun Surgery)。

三问任一不过,回退到「不改」或「重设计」,不许硬修。


骨架优先(文档场景专用规矩)

新写和大改文档时,单独一条硬约束:骨架先立,内容后填,过渡最后加(对应 Outline-First):

  1. 先列骨架:每一节一句话观点,顺一遍能不能立住、之间有没有承启。
  2. 骨架顺了,再填内容:每一节内容展开。
  3. 最后加过渡:章节之间的承启句,让整篇喘得上气。
  4. 改了任何一节,回骨架重扫一遍:骨架被破坏了就重来,不许打补丁维持假连贯。

产出:改前通读报告

三步都过完,给一份报告(中重档写下来,轻档在心里过并口头说):

【改前通读报告】

## 通读了什么
- 载体:文档 / 技能文档 / 方案
- 读的范围:...(具体到文件、章节)
- 读到什么程度:...

## 影响面清单
- 这次要动的点:第 N 节「XX」
- 跟这个点相关的既有逻辑:
  - [章节/位置]:...
  - [章节/位置]:...

## 三问回答
1. 这个点历史上动过吗?
   → 未动过 / 动过:[章节 / 版本],历史结论是「...」
2. 修法风险比原问题大吗?
   → 不大,理由:... / 大,换修法:...
3. 会破坏整体骨架吗?
   → 不破坏,理由:... / 破坏,决定回骨架:...

## 决定
- [ ] 改(按上面结论动手)
- [ ] 不改(理由:原有机制能兜住 / 修法风险大)
- [ ] 回骨架重设计(理由:硬插会破坏一致性)

三问任一不过,给「不改」或「回骨架」,不许硬修。


反模式硬禁止

  • 「先改上再说,以后统一整理」:补丁摞补丁的入口,禁止。
  • 「小问题快速改一下,不用看那么多」:「小」和「快」是补丁的两个借口,不成立。
  • 「只改这一处,不动其他的」:不看整体就不知道要不要动其他。
  • 「说优化就逐句润色」:没指改哪儿时只抠措辞,论据放错节、结论收不全这类骨架病全漏掉。先抽骨架再动。
  • 「新增的挂在末尾,不影响原文」:挂在末尾也是骨架的一部分,不融就是补丁。
  • 「上次刚删的又加回来」:文档 / 版本历史都不看,禁止。
  • 「一遍改一遍看效果,来回反复」:是没通读整体的症状,回第一步。

力度与豁免

软约束,不阻断交付:

  • 重档(对外文档 / 已发布技能文档更新):三步全跑,报告写下来。
  • 中档(内部文档修改 / 手记类):三步跑,报告口头说清。
  • 轻档(拼写、typo、格式微调、明显笔误):可跳过,但要在心里过一遍,这真的只是 typo 吗?

豁免:一次性丢弃的草稿、纯一句话答疑,可以跳过。豁免要在心里对自己说一句「这是草稿,不是产出」,能说出口才算数。


出稿前自检

  • 通读做到位了吗?(文档通读全文了吗?技能看了所有 references 吗?)
  • 影响面清单列全了吗?
  • 三问答完了吗?任一"不过"有没有硬修?
  • 有没有踩到"上次已删的又加回来"这条?
  • 骨架还立得住吗?

任一答不上,回去补。软约束不是可跳过,是"跑不过不阻断,但要显式说出豁免理由"。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sansi Erhouxing AI skill do?

三思而后行:改任何已成形的文档之前(写文章、改稿、调研、方案、技能文档),先通读全文骨架再动手,别只盯一段、别补丁摞补丁。这是前置动作技能,跟写作/改稿技能并行、先于它们跑,不是二选一:它管「动手前先看整体」,写作类技能管「怎么写好」,两层都走,先三思再动笔,别因带了"润色""精简"就跳过。最典型、命中必用:改文档、补一段或一节、精简/润色/优化/压缩/扩写已有段落、新增章节、按评审意见改稿。触发词:改文档、改稿、补内容、加一节、改一处、改一段、顺手改、只改这一处、润色、精简、优化、通篇优化、整篇改、压缩、扩写、顺一顺、通篇顺一顺、调措辞、重写这节、评审意见、反馈意见。DO NOT USE WHEN:从零新起一篇、纯一句话答疑、代码/工程改动(交给专门的验证流程)。

Why use Sansi Erhouxing on TypingMind?

Because you install it once and use it with any model. Sansi Erhouxing 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 Sansi Erhouxing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Job-Yang/jobyang-ai-skills/tree/main/skills/sansi-erhouxing. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sansi Erhouxing?

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 Sansi Erhouxing?

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

Is the Sansi Erhouxing AI skill free?

Yes. It is published on GitHub by Job-Yang 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇