Home / whishi47 / yangmou-skill · GitHub

yangmou SKILL.md skillA

yangmou from whishi47/yangmou-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add whishi47/yangmou-skill/yangmou@git:20260723.e001cd6

Pins git:20260723.e001cd6 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
whishi47/yangmou-skill
Path
SKILL.md
Versions recorded
4
Latest version
git:20260723.e001cd6, committed Jul 23, 2026
First version recorded
Jul 22, 2026
Size
9,280 bytes
Repository stars
3
License
MIT

跨 AI 工具通用的阳谋师 Skill（Agent Skills 标准，兼容 WorkBuddy / OpenAI Codex / Claude Code / Cursor / OpenCode 等）——把"明牌博弈"方法论系统化地应用于销售、营销、管理、职场、投资、产品、谈判七大人际与商业博弈领域。当用户要"搞定难缠客户、谈价压价、锁客复购、在竞争中不可逆地赢、设计光明正大的策略、或拿到对方明知却不得不就范的打法"时触发。工作流：① 四轮询问锁定真实局面（场景定位→对手画像→我的筹码→约束红线）；② 调用 scripts/retrieve.py 从 88 条可溯源案例检索原型——73 条原典覆盖《孙子兵法》《鬼谷子》《三十六计》《长短经》《资治通鉴》《君主论》《战争论》等十部古今战略经典（含真实原文引文与出处 URL），另 15 条特斯拉、Costco、网飞、华为等经典商业案例；③ 六层语义分析：解构→识别锁死机制（规则/人性/大势三支柱）→匹配原型→现代领域翻译→设计明牌/造势→反制推演；④…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 阳谋师 Skill

## 概述

阳谋 = 明牌博弈：把策略摊在阳光下，对手看穿了也因为规则、人性或大势的约束而不得不按你的剧本走。本 skill 把阳谋方法论变成一套可复用的"求解引擎"，**覆盖销售、营销、管理、职场、投资、产品、谈判**七领域，并重对待、不偏科——古案经现代迁移可适配全部领域，由用户在首轮确认具体领域。**

求解不是给"建议"，而是设计一个让对方"两害相权取其轻 / 两利相权取其重"、自然走向你要的结果的**明牌**。

**为什么"纯灌原书 ≠ 能用"**：《孙子兵法》《鬼谷子》是古代语境，直接照搬用不上。本 skill 的关键是把每个古案抽成**可迁移的锁死机制**（规则/人性/大势三支柱），再用现代语汇（锚定/稀缺/标准/透明/切换成本…）翻译到目标领域。迁移方法论与对照表见 `references/现代领域迁移.md`。

## 何时使用

- 用户要"赢一个局"：搞定客户、谈下价格、拿下订单、锁客、在竞品中胜出。
- 营销破局：心智占领、裂变、定价、信任重建、规则重构。
- 管理/职场：化解部门阻力、推进跨部门项目、上位不被反噬。
- 投资/产品/谈判：低价入局高价退出、定义赛道、让对方主动让步。
- 用户问"阳谋""光明正大的策略""让对手无解的打法""换个思路解决这个局"等。
- 用户描述一个具体的博弈困境，希望拿到可落地的破局方案。
- 不适用于：纯信息查询、写文案、做表等不涉及"博弈破局"的任务。

## 核心概念（按需加载）

- 阳谋原理、与阴谋的区别、三支柱（规则/人性/大势）：读 `references/阳谋原理.md`。
- 商业多场景映射、四轮询问提问库、六层分析（含现代领域翻译）、输出模板：读 `references/阳谋多场景.md`（七领域并重，含多领域情境映射）。
- **古案→现代迁移方法论、三支柱现代翻译、营销心理学↔阳谋 / 销售定价模式↔阳谋 两张对照表、迁移工作表**：读 `references/现代领域迁移.md`。**做非销售领域或"换思考"时必须读。**
- 案例事实底座（**88 条**结构化案例 = 15 历史/商业 + **73 原典·含真实原文**，含 `transfer_models` 通用思维模型与 `fields` 多领域打法）：`references/cases.json`，通过 `scripts/retrieve.py` 检索，不要手敲。
- 可继续灌入的书目与拆解规范：`references/书籍索引.md`。

## 工作流程

### 第 0 步 · 接收问题
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add whishi47/yangmou-skill/yangmou@sha256:7d15d57d8e75ff7c

The line at the top of this page pins the label git:20260723.e001cd6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_vxq7z5fxjrt6jkgf.svg)](https://markdownregistry.com/a/art_vxq7z5fxjrt6jkgf)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jul 22, 2026 and Jul 23, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20260723.e001cd6 latest2026-07-23 e001cd6 9,280 BA view · diff
git:20260723.0d872a82026-07-23 0d872a8 9,326 BA view · diff
git:20260723.5e4e1ad2026-07-23 5e4e1ad 8,932 BA view · diff
git:20260722.b43b8312026-07-22 b43b831 8,813 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9280 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

whishi47/yangmou-skill · 3 stars · license MIT · pushed 2026-09-10 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vxq7z5fxjrt6jkgf
GET https://markdownregistry.com/api/v1/resolve?ref=whishi47/yangmou-skill/yangmou
GET https://markdownregistry.com/api/v1/blob/7d15d57d8e75ff7ccf61909dd8068db5b4874b949f5f6b09d817f8c418c719b1

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.