Not in the top 1,000 by GitHub stars

ayi-ai/ayi-nonviolent-communication

马歇尔·卢森堡《非暴力沟通》(NVC) 的可执行 AI Skill:把任何一句话翻译成 观察-感受-需要-请求。Cursor / Claude Code 可直接安装。

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → edd2d0773679

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit edd2d077367978a462ec1a94ec440bc34014ae2b

194GitHub stars
6stars in 7 days
1skill in this repository
0commits in 30 days

Heat

3.5
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 3, 2026194

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

ayi-nonviolent-communication

When your agent uses it

马歇尔·卢森堡《非暴力沟通》(NVC/善意沟通/长颈鹿语言) 的可执行工具箱。核心引擎是把任何信息(自己的或他人的)翻译成"观察—感受—需要—请求" (Observation-Feeling-Need-Request) 四要素,重新与普世"需要"连结。覆盖五类用法:① 决策/自我教练(理清自己的需要再行动); ② 话术改写(把指责/评判式表达改成 NVC 表达); ③ 同理倾听(听见对方话语背后的感受和需要); ④ 冲突调解/复盘(区分需要vs策略,设计满足各方的方案); ⑤ 以马歇尔的语气产出内容。当用户要"帮我想想怎么说/这话该怎么回""我该不该做这个决定/理一理我现在的情绪""改一下这条消息别那么冲" "他这么说我该怎么回应/怎么劝""化解一段冲突/调解吵架/复盘一次难谈话""表达感谢/反馈/批评""我好生气/好委屈/好内疚怎么办", 或提到 非暴力沟通 / NVC / 善意沟通 / 长颈鹿语言 / 豺狗 / 观察vs评论 / 感受vs想法 / 需要 / 请求vs要求 / 同理心 / 卢森堡 / 马歇尔 时使用。

What it loads into context

Frontmatter

371 tokens

Always available to the agent

SKILL.md

1,806 tokens

When the skill is activated

Reference documents

7,618 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 哲学(先记住这 4 条)
  2. 调用本 skill 时必须做的
  3. 意图路由表(按用户意图读对应 reference)
  4. 核心区分速查(最常出错的地方)
  5. 四要素的硬标准(表达时)
  6. 关键原则
  7. 反模式总靶:疏离生命的语言(豺狗语言)

Files

  • LICENSEasset1,075 bytes
  • README.mddoc3,717 bytes
  • SKILL.mdcore5,742 bytes
  • cover.pngasset1,860,163 bytes
  • references/anger-conflict-force.mddoc5,308 bytes
  • references/anti-patterns.mddoc3,652 bytes
  • references/empathy-and-self.mddoc5,323 bytes
  • references/engine-four-components.mddoc4,364 bytes
  • references/voice-and-gratitude.mddoc2,784 bytes
Read SKILL.md

# 非暴力沟通 (Nonviolent Communication)

源自马歇尔·卢森堡《非暴力沟通》(修订版)。这不是"好好说话技巧",而是一种**意识**:与生命/需要连结。语言只是载体。

## 哲学(先记住这 4 条)

1. **唯一引擎是四要素**:观察(O)→感受(F)→需要(N)→请求(R)。全书每一章都是这台引擎换个场景运转。
2. **两个方向,同一引擎**:诚实**表达自己**(我观察…我感到…我需要…我请求…) 与 同理**倾听他人**(你看到…你感到…你需要…你希望…?) 用的是同一组四要素。
3. **一切冲突/暴力都源于遮蔽了"需要"**。人所有言行都是在尝试满足某种普世共通的需要;评判、比较、推责、要求(=豺狗语言)把需要藏了起来。把信息翻译回需要,由衷的给予自然流动。
4. **慢下来**。这是马歇尔的元指令——停下、深呼吸、给自己时间,再开口。

## 调用本 skill 时必须做的

1. 先按下面的**意图路由表**判断用户要做什么,**只读需要的 reference**(懒加载,不要一次全读)。
View the complete source on GitHub

Skills included

  • ayi-nonviolent-communication

Repository facts

License
MIT
Created
May 31, 2026
Last pushed
May 31, 2026
Forks
30
Open issues
0
Project activity
Slowing

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 6, 2026

  • No broad tool permissions
  • No dangerous shell commands
  • 3 network referencesin 1 file: README.md:12
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 3 signals by file

README.md

  • Network accessline 12
    [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](./LICENSE)
  • Network accessline 59
    git clone https://github.com/ayi-ai/ayi-nonviolent-communication.git \
  • Network accessline 66
    git clone https://github.com/ayi-ai/ayi-nonviolent-communication.git \

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 3 facts
  • Network access in prose of documentationREADME.md:12Low confidence
  • Network access in code of documentationREADME.md:59Low confidence
  • Network access in code of documentationREADME.md:66Low confidence

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.