F01 Retreat Step

Q: What does the F01 Retreat Step AI skill do?

当用户在谈判、争执、僵持或博弈局面中说"要不要让一步"或"要不要退"时调用。 也适用于：对方态度强硬、双方陷入僵局、感觉再进一步就会撕破脸的情境。 不适用于：纯信息查询、日常闲聊、对方已完全服软。

Community

ace3000chao

f01-retreat-step

当用户在谈判、争执、僵持或博弈局面中说"要不要让一步"或"要不要退"时调用。也适用于：对方态度强硬、双方陷入僵局、感觉再进一步就会撕破脸的情境。不适用于：纯信息查询、日常闲聊、对方已完全服软。

Overview

Publisher	ace3000chao
Repository	`book2startup`
Skill name	`f01-retreat-step`
Stars	93
Forks	14
Bundled files	1
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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by ace3000chao on GitHub. Read the source before you install it.

Installation

Install the F01 Retreat Step 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/ace3000chao/book2startup/tree/master/菜根谭skills/skills/f01
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.

Use it in TypingMind

Enable F01 Retreat Step 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 F01 Retreat Step 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 F01 Retreat Step 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.

退让一步决策框架

R — 原文 (Reading)

"处世让一步为高，退步即进步的张本；待人宽一分是福，利人实利己的根基。"

— 洪应明, 菜根谭·忍让为高利人利己

I — 方法论骨架 (Interpretation)

退让不是认输，而是以退为进的战略动作。

这个框架的核心逻辑是：人与人在资源、立场、面子上的冲突，本质上是一场"谁先退谁赢"的博弈。先退一步的人，并不是输了，而是在积累势能——因为退让换来的空间，可以在下一次需要时重新占据。真正的收益不是眼前的得失，而是关系和局面的长期健康。

方法论步骤：

判断当前局面是否已陷入"顶牛"——双方都在僵持，谁也不让谁，情绪在升温。
评估"不让"的代价——正面冲突、关系破裂、机会丧失、时间浪费，这些成本有多高？
让一步的空间在哪里——不是全部放弃，而是找一个"局部退让、保留核心"的方案。

一句话总结： 退一步不是失去，而是买入未来的资本。

A1 — 书中的应用 (Past Application)

案例 1: 范蠡张良功成身退

问题: 范蠡辅佐越王勾践灭吴，张良辅佐刘邦立汉，两位开国功臣都面临功高震主的危险局面。
方法论的使用: 二人都识别到"盛极必衰"的天道规律，主动选择急流勇退，放弃眼前巨大的权力和利益。
结论: "退步即进步的张本"——退让为他们的后半生赢得了自由、安全和后世的千古美名。
结果: 范蠡经商成为"陶朱公"，富甲一方；张良隐居修道，善终而名垂青史。与之对比，李斯贪恋权位，最终被腰斩、夷三族。

案例 2: 霍光子孙骄奢身死族灭

问题: 霍光受汉武帝托孤，辅政二十年，家族显赫，本可善终。
方法论的使用: 霍光未能识别"盛极而不知退"的危险信号，子孙在权势鼎盛时不知收敛，骄奢淫逸。
结论: 当权时不退，则子孙承受祸端。
结果: 霍氏满门被诛，家族覆灭。印证了"退步即进步的张本"——不退则进无可进。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

谈判僵局：双方在商务谈判、合作条款、合同细节上僵持，对方态度强硬，你感觉再争下去就要谈崩。
人际冲突升级：和朋友、家人、同事发生争执，双方都在气头上，你意识到再顶下去关系会破裂。
职场站队压力：团队内部出现派系斗争，你需要表态但不想选边，想找到"不选边也能存活"的空间。
利益博弈：商业合作中对方压价或提出苛刻条件，你判断接受太亏、不接受太伤，想找第三条路。
荣誉地位受到挑战：在公开场合被人挑衅、质疑、抢风头，你纠结于当场反击还是忍让。

语言信号 (用户的话里出现这些就应激活)

"要不要让一步？"
"感觉再争下去就撕破脸了"
"他这个态度我该怎么应对，是硬刚还是软一点？"
"这个条件我能答应吗？还是再谈？"
"要不要退一步？"
"我不想把关系搞僵，但也不想太吃亏"
"对方已经很强硬了，我在想要不要服软"

与相邻 skill 的区分

与 f09（天理人欲分判框架） 的区别：f09 问的是"这条路对不对"，f01 问的是"这条路要不要退着走"——一个判断方向，一个选择节奏。
与 f11（舍己勿疑施恩勿报框架） 的区别：f11 关注的是"舍己的德行是否纯粹"，f01 关注的是"退让的战略收益"——一个是动机纯度，一个是策略效率。

E — 可执行步骤 (Execution)

当 skill 被激活后，agent 应按以下步骤执行:

识别僵局类型
- 完成标准: 明确说出"这是资源型僵局（争利益）"、"关系型僵局（争面子）"还是"立场型僵局（争对错）"。
评估不让的代价
- 完成标准: 列出"如果这次不让，可能发生的三个最坏结果"（用"关系破裂""机会丧失""时间损失"等维度评估）。
- 判停条件: 若评估结果显示代价只是"面子受损"且可修复，则进入下一步；若是"根本利益受损"且不可逆，则提示用户重新判断。
寻找"最小有效退让"
- 完成标准: 给出一个具体的退让方案——不是"全让"也不是"不让"，而是"在这个点上退一步，可以换取哪些具体收益"。
- 判停条件: 若找不到"退让收益比>1"的方案，则提示用户"可能需要重新评估当前局面是否值得继续"。

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

对方没有诚意，只是试探你的底线：此时退让等于示弱，只会让对方得寸进尺。
核心利益被触动，且无法分割：如果你坚守的底线一旦退让就等于完全放弃核心价值，则不应该退让（比如涉及人格、尊严、原则的核心问题）。
对方是恶意打压，不是正常博弈：遇到故意找茬、人身攻击、恶意诋毁，此时不应退让，而应反击或止损。

作者在书中警告的失败模式

快意不知回首（ce03）：春风得意时不知见好就收，贪恋权位不肯急流勇退。表现为：处于巅峰时愈发贪婪、不愿接受任何退让、享受众人吹捧不能自拔。
倚物役心（ce17）：被外物奴役，逆顺皆苦。表现为：患得患失、别人的评价能让自己高兴或痛苦很多天。

容易混淆的邻近方法论

退让 vs 投降：退让是有底线的策略性后退；投降是放弃底线的全面溃败。本框架要求"保留核心，只退边缘"。
退让 vs 逃避：退让是"正面面对但选择合适的节奏"；逃避是"不面对而绕开"。本框架要求主动选择，而非被动逃离。

审计信息

验证通过: V1 ✓ / V2 ✓ / V3 ✓
测试通过率: N/A (待填充)
蒸馏时间: 2026-04-24

Bundled files

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

test-prompts.json4 KB

Frequently asked questions

What does the F01 Retreat Step AI skill do?

Why use F01 Retreat Step on TypingMind?

Because you install it once and use it with any model. F01 Retreat Step 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 F01 Retreat Step in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ace3000chao/book2startup/tree/master/菜根谭skills/skills/f01. 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 F01 Retreat Step?

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 F01 Retreat Step?

As many as you like. As long as a model supports skills, you can use F01 Retreat Step with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the F01 Retreat Step AI skill free?

Yes. It is published on GitHub by ace3000chao 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

Issue Reporter

CherryHQ

OrganizationPopular

只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发，必须改用 cherry-studio-feedback 并默认提交飞书。

Skills Manager

搜索、安装和协调创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill，或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a skill"时触发。也适用于用户说"有没有做 X 的工具"、"我想扩展 Agent 能力"，或当前能力不足需要先查找可复用方案的场景。

Cli Anything 3mf

3MF mesh geometry editor — detect and resize cylindrical holes, repair meshes, compare 3D printing files. Works with BambuStudio and PrusaSlicer 3MF files.

Cli Anything Godot

Agent-native CLI for Godot project management, scenes, exports, and script execution.

F01 Retreat Step

Overview