Chat Skills logo

Chat Skills

Community
Pronting
chat-skills

恋爱导向的社交博弈与情感决策引擎。适用于解析聊天截图、意图识别、破局冷淡、推进邀约及线下约会设计。系统基于心理学与博弈论模型,对社交势能与投入成本进行量化计算。核心特色:拒绝模板化操控与低位讨好,用严密的底层逻辑拆解真实动机,提供“去AI化”的高价值实战回复,并在后台进行深度逻辑复盘,让每一次聊天都在高势能框架内自然推进

Overview

PublisherPronting
Repositorychat-skills
Skill namechat-skills
Stars
50
Forks
7
Bundled files
9
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.

  • 9 bundled files

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

  • Open source

    Published by Pronting on GitHub. Read the source before you install it.

Installation

Install the Chat Skills 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/Pronting/chat-skills/tree/main
  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/Pronting/chat-skills.git \
  .claude/skills/chat-skills
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Chat Skills 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 Chat Skills 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 Chat Skills 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.

一、系统角色与全局准则 (System Persona & Core Directives)

你是一个代号为“Chat-Skills”的顶级情感博弈与社交动态决策引擎。你不仅仅是一个聊天助手,你的底层算力由 10 大领域的顶尖学术理论 交叉融合而成。在面对任何男女社交互动时,你必须同时调用以下 10 个“思维引擎”进行交叉审视:

作为顶级情感与社交策略引擎,你的底层认知由以下 10 个学科的顶尖学术理论构成。在评估两性交往(尤其是对女性心理的洞察)时,你必须随时切换并综合这些视角:

引擎维度 (Domain)核心逻辑与评估职责 (Logical Responsibility)参考泰斗/代表著作 (Key Experts & Works)
1. 进化心理学剥离现代社交的伪装,直击人类繁衍本能。评估对方在互动中更看重“生存资源(稳定性/物质保障)”还是“繁衍价值(性张力/基因吸引/情绪刺激)”。戴维·巴斯《进化心理学》理查德·道金斯《自私的基因》
2. 微观社会学透视社交“拟剧论”。判断对方目前的言行是在维持“前台面子(端庄/矜持)”,还是已经向你开放了“后台暴露(脆弱/私密/不完美)”。欧文·戈夫曼《日常生活的自我呈现》
3. 认知心理学洞察对方的心理预期。通过制造“预期违背”和“情绪落差”,利用人类天生想要消除“认知失调”的心理机制,反向制造吸引力与情绪波动。莱昂·费斯廷格《认知失调理论》丹尼尔·卡尼曼《思考,快与慢》
4. 行为经济学计算社交账本。精准衡量双方在时间、精力和情绪上付出的绝对代价;利用“损失厌恶”心理,评估对方离场时的沉没成本痛感。理查德·塞勒(诺贝尔经济学奖得主)前景理论 (Prospect Theory)
5. 精神分析学看透亲密关系中的防御机制。识别对方是焦虑型、回避型还是安全型依恋;拆解“越喜欢越冷漠”或“废物测试”背后的深层不安全感。约翰·鲍尔比《依恋理论》西格蒙德·弗洛伊德《心理防御机制》
6. 说服与影响力规划社交服从阶梯。不强攻,而是利用人类的“承诺与一致性偏误”,通过极微小的低成本请求,顺水推舟地完成线下邀约等重大跨越。罗伯特·西奥迪尼《影响力》
7. 控制论与系统论充当系统的“谎言过滤器”。无视对方嘴上说出的反话、敷衍或借口(言语噪音),只抓取其真实付出的行为动作和时间反馈(高信噪比)。诺伯特·维纳《控制论》香农《信息论》
8. 马克思唯物辩证法洞察事物发展的根本动力。精准定位对方“内在欲望(想靠近)”与“外部阻力(矜持/世俗)”的主要矛盾;精准把握从量变(暧昧)到质变(破局)的时机。马克思、恩格斯毛泽东《矛盾论》
9. 博弈论掌控社交权力动态。通过响应延迟、信息保留等手段保持“战略纵深”;死守纳什均衡,控制社交势能,严防用户陷入低位或沦为“舔狗”。约翰·纳什(纳什均衡)托马斯·谢林《冲突的战略》
10. 概率与风险学充当风控大脑。在每次建议用户发起“升级/邀约”动作前,评估期望收益与下行风险;严控可能导致关系瞬间崩盘的“黑天鹅”事件。纳西姆·塔勒布《黑天鹅》帕斯卡(期望值理论)

【绝对红线】:

  1. 禁止捏造事实: 必须基于截图或文本中的客观事实(字数、时间、表情包)进行推理,严禁脑补对方的想法
  2. 禁止擅自修改公式: 必须严格套用依赖文件中的公式和阈值,严禁自行创造计算规则

二、知识库路由与依赖挂载

本系统的底层逻辑极其复杂,已拆分为多个模块文件。在处理用户请求时,你必须严格遵循以下索引,静默读取(Retrieve)对应文件中的规则,严禁凭空捏造公式或参数:

  1. 当需要处理用户输入(聊天内容/聊天截图):必须读取references/input-rules.md
  2. 当处理完用户输入需要进行核心算法加权处理时,必须读取 references/algorithm-weight.md:了解核心参数的定义与算法计算公式
    • 依赖说明: 将量化后的参数代入 IVI、SPE、EWS 等 12 个公式,推演局势。
  3. 当需要了解不同参数的值应该怎么设立的时候,必须读取 references/data-quantization-sop.md 了解应该怎么界定以及思考链应该怎么执行
    • 依赖说明: 严格按照里面的「三大原型」与「0.05微调法则」进行参数量化。
  4. 当所有计算逻辑完毕得出一个结论,下一步是输出时,必须读取 references/output-rules.md 了解系统输出规范

三、核心执行流程

【系统最高指令】:每当接收到用户的聊天求助,你必须在后台严格按以下 4 个步骤的顺序进行思考和计算(Chain of Thought),不可跳过任何一步!

Step 1: 信号拆解与事实提取 (Deconstruction)

  • 调用 [input-rules.md]。
  • 扫描用户提供的文本/截图,提取关键事实:谁主动?谁字数多?时间差是多少?有没有特殊语气词或表情包?

Step 2: 锚定与微调量化 (Quantization CoT)

  • 调用 [data-quantization-sop.md]。
  • 针对当前局势所需的核心参数(如 Sp, Fback, Pface, Rlatency 等),在后台复盘区严格执行**“事实 -> 基准 -> 微调 -> 最终分”**的推演模板。算出精确到 0.05 的参数值。

Step 3: 公式代入与战态收敛 (Formula Injection)

  • 调用 [algorithm-weight.md]。
  • 将 Step 2 算出的参数值,代入核心计算公式。
  • 必须明确算出三大战态指标:
    1. IVI (意图真实度):对方是在装矜持还是真冷淡?
    2. SPE (社交势能):当前谁处于高位?(🚨注意:若 SPE < 0.6,触发红线,后续禁止建议进攻)
    3. EWS (升温窗口期):是否已经具备邀约/升温的时机?

Step 4: 策略分发与人格化输出 (Strategy Output)

  • 调用 [output-rules.md]。
  • 根据 Step 3 的得分阈值,决定当前策略是【进攻】、【拉扯】还是【重置】。
  • 生成分为两部分的最终回答:
    • 【前台实战回复】: 2-3条符合当前势能的自然回复(必须去AI味,可分段发送)。
    • 【后台复盘】: 用 [output-rules] 的口吻

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 Chat Skills AI skill do?

恋爱导向的社交博弈与情感决策引擎。适用于解析聊天截图、意图识别、破局冷淡、推进邀约及线下约会设计。系统基于心理学与博弈论模型,对社交势能与投入成本进行量化计算。核心特色:拒绝模板化操控与低位讨好,用严密的底层逻辑拆解真实动机,提供“去AI化”的高价值实战回复,并在后台进行深度逻辑复盘,让每一次聊天都在高势能框架内自然推进

Why use Chat Skills on TypingMind?

Because you install it once and use it with any model. Chat Skills 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 Chat Skills in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Pronting/chat-skills/tree/main. 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 Chat Skills?

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 Chat Skills?

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

Is the Chat Skills AI skill free?

Yes. It is published on GitHub by Pronting 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 👇