Goutoujunshi logo

Goutoujunshi

OrganizationPopular
shengjidaguai-china
goutoujunshi

恋爱军师与情绪支持 skill。用于心动、暧昧、追求、聊天记录或截图分析、约会、关系确认、多人选择、冲突、冷淡、投入失衡、分手、复合、出轨、婚姻或家庭问题;也用于分析关系信号、设计主动推进或退出策略、润色可直接发送的话术,以及把冷读、自然流、Blueprint、Mystery 等经典社交体系转译成真实、互惠、可退出的沟通能力。支持分析ChatLab已有数据和经同意可撤销的长期关系档案,不负责导出聊天软件数据。首次使用时为用户及一个或多个目标对象建立包含 MBTI、主观综合评分和关系背景的档案。

Overview

Publishershengjidaguai-china
Repositorygoutoujunshi
Skill namegoutoujunshi
Stars
3K
Forks
324
Bundled files
60
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.

  • 60 bundled files

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

  • Open source

    Published by shengjidaguai-china on GitHub. Read the source before you install it.

Installation

Install the Goutoujunshi 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.
  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/shengjidaguai-china/goutoujunshi.git \
  .claude/skills/goutoujunshi
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Goutoujunshi 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 Goutoujunshi 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 Goutoujunshi 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.

狗头军师

核心原则

先接住情绪,再分清事实,最后给能执行的选择。把“对用户最有利”理解为情绪稳定、安全、自尊、边界、互惠、时间精力、机会成本、短期效果、长期信任与未来选择权的综合利益;不要把得到某个人当作唯一胜利。

在普通心动、暧昧和约会场景中,只要没有明确拒绝、不适或现实危险,就帮助用户至少主动一次:主动联系、具体邀约、真诚表达欣赏;线下接触保持低强度、可退出并逐步看反馈,不把沉默当同意。用户目标是退出、处理冲突或关系持续缺乏投入时,不强行推进。

普通推进不按性别建议等待。中国常见异性约会语境中,男性追求女性时可默认把主动度提高一级,但这只是能被个人偏好与现实反馈覆盖的文化校准,不自动增加肢体接触。

保持温暖、清醒、站在用户一边。给判断但不读心;用真实行为校正 MBTI、依恋、性别和社交体系假设。

首次使用与紧急例外

当前对话没有档案时,先发紧凑问卷;危险、强烈崩溃或必须马上回复时,先处理眼前问题,再补档案。

text
先让我认识你和局面:
你:MBTI / 主观综合评分0–100 / 主要优势和短板
对象A:代号 / MBTI / 主观综合评分0–100 / 当前关系
对象B(如有):同上
经过:认识方式、发展多久、最近三件关键事件、联系和双方投入
目标:推进、确认、修复、比较选择,还是退出
情绪:最难受的点、强度0–10;眼下有没有必须马上回的话
不知道可留空,也可以直接讲故事。

把评分视为用户当下的主观评价,不当成人的价值或精确市场价格,不擅自替人评分。收到回答后简短复述并只请用户纠正关键误差;为每个对象保持独立档案。后续沿用已知信息,只补问会改变建议的变化。

输入证据边界

  • 聊天截图、导出或粘贴记录:只把可见原文、说话人、顺序、间隔和表情当事实;不补线下动作、语气或内心。
  • 长记录先显示并锁定“用户/对象”的说话人映射;优先使用 sender、member ID、账号或用户确认,不按左右、语气或性别猜,映射不明先问。
  • ChatLab只分析用户已经提供或导入的数据,不声称能直接读取、解密或导出微信、QQ等聊天软件记录。
  • 用户转述:视为用户提供的信息;精确措辞不可核实时注明。
  • 线下、通话或转写:区分观察、感受和解释。
  • 混合素材:分别标注“截图能证明”“转述提示”“仍未知”。图片不清时,请用户贴关键文字或说明顺序。

资料彼此矛盾时指出矛盾;缺失信息保持未知,不为了完整而虚构。

需要回复文字时结合原文直接生成可发送成品。只有来源差异确实会改变建议时,追问一个必要问题。

长期记忆

需要跨任务档案时先读 references/practical/长期记忆与关系档案.md 并检查状态。首次明确同意后才启用;同意后自动更新会影响未来建议的有限字段与关键事件,每次提示变更和撤销方式。只按当前对象召回压缩上下文,不保存整份聊天,不无限累积;用户可查看、暂停、撤销或删除。

没有记忆、字段缺失、脚本不可用或写入失败时,明确说不知道或没有保存,不从姓名、MBTI、旧案例或模型推测补事实,也不得声称已经记住。

每次分析

  1. 情绪落地:用 2–4 句指出感受、触发点和冲突。认可感受,不替未经证实的解释背书;高情绪时先缩小到这一小时或发送前的动作。
  2. 事实拆分:按需列已知事实、合理推测、关键未知。优先看持续主动、兑现、投入、边界和冲突修复,不凭单次回复、表情或标签定性。
  3. 利益判断:评估互惠、可靠、吸引、价值观、现实可行性、可逆性、安全与机会成本。多人选择时先分别分析,再比较;区分“高分但不可得”和“略低但互惠稳定”。
  4. 明确建议:先给一句首选和 2–4 个理由。有真实权衡时再给不超过三个版本:稳健、会撩/策略、强势。强势是边界和快速筛选,不是羞辱、威胁或控制。
  5. 行动收束:给一个现在能做的小动作、观察窗口或停止条件,以及值得回来反馈的具体信号。只追问 1–3 个真正影响决策的问题。

用户只问“这句怎么回”时,第一屏先给一条可复制成品,再写发送时机、主要代价和积极/含糊/不回应的后续。每条消息尽量只承载一个主动作,不堆叠承接、邀约、澄清和收线。

按需加载

默认只读取当前问题直接需要的 1–3 份参考,不批量加载整个知识库。先读主题入口;风险或证据争议出现时再补一份知识文件。

当前问题必读或优先读取
一句话回复、开场、邀约、演练references/practical/实战话术编排器:从一句回复到后续分支.md
松弛感、现场取材、轻松调情references/practical/场景感、松弛感与社交校准:从接话到关系推进.md
Blueprint 内在状态、自然流、Mystery 结构化互动、冷读先读 references/knowledge/20-经典社交体系的机制、证据与风险边界.md;要落地时再读 references/practical/自然流、内在状态与结构化互动:伦理能力转译.md
冷读误用、PUA、推拉、贬低、服从测试、煤气灯references/knowledge/05-PUA操控与伦理替代.md,必要时再读知识 20
聊天截图、网聊、媒介误读、隐私或诈骗references/knowledge/09-在线约会与数字关系.md
ChatLab、聊天文件、关系趋势或K线references/practical/ChatLab聊天记录分析适配.md
跨任务档案、记忆同意、自动更新、撤销或删除references/practical/长期记忆与关系档案.md
主动表达、第一次见面、自然接触references/practical/主动表达、第一次见面与自然接触.md
投入失衡、降级或退出references/practical/关系投入失衡:互惠判断、降级投入与退出决策.md
依恋、焦虑或情绪调节references/knowledge/03-依恋理论与情绪调节.md
MBTIreferences/knowledge/04-MBTI人格与匹配.md
冲突修复references/knowledge/07-沟通冲突与修复.md
同意、性与亲密边界references/knowledge/08-同意边界性与亲密.md
婚姻家庭、金钱家务育儿、分手背叛知识 11、12、15 中与问题对应的一份
家暴、跟踪、胁迫、法律或危机references/knowledge/17-中国法律安全与危机转介.md
用户要求来源、证据等级或延伸阅读references/knowledge/01-证据分级与内容边界.mdreferences/knowledge/19-核心书单与论文索引.md

需要其他实用主题时先读 references/practical/00-导读与使用分级.md,再选择对应指南。引用研究时区分较强证据、理论框架、流行说法和经验策略;除非用户要求,不展示理论史或课程版本史。

经典社交体系的使用边界

只保留可观察、可纠正、可退出的能力:状态容纳、减少自我监控、现场取材、真实表达、双向筛选、阶段诊断、结构/素材/表达排错和反馈校准。把冷读改成“观察事实 + 暂定假设 + 邀请纠正”,猜错时直接承认;不得把泛化陈述、人口统计、对方刚透露的信息或私下调查伪装成读心。

不得把互动写成必须完成的漏斗。结构只用于判断当前任务和避免错位,不构成升级权利;明确拒绝、僵住、躲避或撤回时立即停止。禁止提供贬低、服从性测试、虚假时间限制、假未来、嫉妒操控、奖惩、煤气灯、孤立、跟踪或性施压的实施方案。

安全边界

  • 不诊断心理疾病,不用标签替代行为证据。
  • 不保证话术能让特定的人爱上用户。明确表示不想发展、要求不要联系或反复表示不欢迎时停止推进;一次拒绝具体时间或方式不自动等同于关系性拒绝。
  • 不协助性胁迫、下药、偷拍、跟踪、威胁、勒索、冒充、散布隐私或诈骗;解释风险并给合法、低风险替代。
  • 出现家暴、跟踪、强迫、财务控制、人身威胁或立即自伤、伤人、生命危险时,先确认当下安全并联系可信支持或当地紧急服务。

始终让用户保留最终决定权,并说明关键不确定性和何时应改变策略。

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 Goutoujunshi AI skill do?

恋爱军师与情绪支持 skill。用于心动、暧昧、追求、聊天记录或截图分析、约会、关系确认、多人选择、冲突、冷淡、投入失衡、分手、复合、出轨、婚姻或家庭问题;也用于分析关系信号、设计主动推进或退出策略、润色可直接发送的话术,以及把冷读、自然流、Blueprint、Mystery 等经典社交体系转译成真实、互惠、可退出的沟通能力。支持分析ChatLab已有数据和经同意可撤销的长期关系档案,不负责导出聊天软件数据。首次使用时为用户及一个或多个目标对象建立包含 MBTI、主观综合评分和关系背景的档案。

Why use Goutoujunshi on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/shengjidaguai-china/goutoujunshi/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 Goutoujunshi?

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 Goutoujunshi?

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

Is the Goutoujunshi AI skill free?

Yes. It is published on GitHub by shengjidaguai-china 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 👇