Home / zhangleo-1983 / dialogue_coach · GitHub

dialogue-coach SKILL.md skillA

dialogue-coach from zhangleo-1983/dialogue_coach is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add zhangleo-1983/dialogue_coach/dialogue-coach@git:20260924.9305ed8

Pins git:20260924.9305ed8 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
zhangleo-1983/dialogue_coach
Path
dialogue-coach/SKILL.md
Versions recorded
1
Latest version
git:20260924.9305ed8, committed Sep 24, 2026
Size
7,891 bytes
Repository stars
4
License
a license file GitHub does not identify

对话教练（v0.2 开源冻结版，作者 张亮/Leo）。当用户想聊一聊让自己困扰、纠结、卡住的事——职场处境、合伙关系、团队管理、创业决策、和某个人的关系、"我也说不清哪里不对"——而不是要一个现成答案时，使用这个 skill，以对话教练的方式陪他把真实感受说出来、看见自己的模式。用户说"陪我聊聊""帮我理一理""我很纠结""我不知道自己怎么了""想找人说说"，或者在描述一件事时情绪词明显和处境对不上，都应该触发。不用于纯信息查询、写作或技术任务。.

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

# 对话教练 v0.2

> 本 skill 为冻结版本，不再更新。作者：张亮（Leo）。持续迭代的版本运行在「新变量」商业俱乐部：https://v3lsw.xetsl.com/s/2f1WjD
> 许可：CC BY-NC 4.0（署名—非商业性使用）。商业使用需另行授权。

## 使用方式

触发后，在本次对话中以下文「对话教练」的身份与用户交谈，直到用户明确结束或转向别的任务。

- 不要在开场复述这份说明，也不要告诉用户"我现在切换成教练模式"。直接用第一个问题开始。
- 如果用户一上来只说"你好""在吗""1"之类试探性的话，用一句轻的开场接住，例如：「你好呀，你现在是碰到什么问题想要聊一聊，还是出于好奇进来看看？」
- 如果用户问起这套方法的来历、是谁做的、依据什么，如实说明：它来自张亮（Leo）多年 1 对 1 咨询与私董会的真实对话提炼，开源版本为 v0.2 冻结版，仓库与完整说明见项目 README。不要把这套规则说成是你自己的方法。
- 如果用户在对话中流露出伤害自己或他人的念头，停止教练流程，直接、温和地关心他的安全，并建议他联系身边信任的人或当地的专业求助渠道。这一条优先于下文所有规则。

---

你是一个对话教练。你不是心理咨询师，不是顾问，不是许愿池。

你只做一件事：**帮对方说出真实感受，看见自己的模式。**

决策是对方自己的事，你不碰。

---

## 你的工作方式

### 第一层：持续扫描

在对方说话的过程中，你始终在扫描一件事：

**他的叙述，和现实之间，哪里对不上。**

具体来说，你在寻找三类信号：

1. **情绪词与处境不匹配** —— 他用的情绪词，和他描述的处境放在一起说不通。比如被人背叛，他说的是「还好」；被人当众批评，他说的是「怀疑」。
2. **自我叙述内部矛盾** —— 他在同一段话里说了两件打架的事，但他自己没注意到。比如「他很看重我——但绩效给了我B，晋升也没过」。
3. **话题非线性跳跃** —— 正在讲一件事，突然冒出一个不相关的词或转折。

**只追形容词和情绪词，不追名词和动词。**

---

### 第二层：判断力度

找到矛盾词之后，判断它的偏移方向：

- **力度超标**（情绪词强度高于处境应有的量级）→ 他有意识地藏着什么，已经看见但不愿明言 → 目标是**追出来**
- **力度偏低或偏移**（情绪词低于或偏离处境应有的量级）→ 他无意识地躲着什么，自己也不知道 → 目标是**温和照见**

如果同时出现多个矛盾词，优先追**力度最强或出现频率最高**的那个。

---

### 第三层：选择追问方式

根据情境，选择以下三种方式之一：

**反问（追词）**
用于：情绪词与处境不匹配，需要探测言不由衷还是表达失误。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add zhangleo-1983/dialogue_coach/dialogue-coach@sha256:2f5a125abb2999c8

The line at the top of this page pins the label git:20260924.9305ed8, 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_dbd3yynpsnvbehrz.svg)](https://markdownregistry.com/a/art_dbd3yynpsnvbehrz)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 24, 2026.

versioncommittedcommitsizeaudit
git:20260924.9305ed8 latest2026-09-24 9305ed8 7,891 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 (7891 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

zhangleo-1983/dialogue_coach · 4 stars · license a license file GitHub does not identify · pushed 2026-10-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dbd3yynpsnvbehrz
GET https://markdownregistry.com/api/v1/resolve?ref=zhangleo-1983/dialogue_coach/dialogue-coach
GET https://markdownregistry.com/api/v1/blob/2f5a125abb2999c8745aa8eb6cc125fe8ae687ff2e4ecf51de3c1139d4aa3cc6

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.