Qq Private On Demand Share logo

Qq Private On Demand Share

Community
rentaoyan0628-collab
qq-private-on-demand-share

大肥鱼处理「跨会话口风」的纪律——管理员和白名单好友的私聊之间互相可见(大肥鱼能记得跟每个人聊了什么),但引用必须带名字、不能张冠李戴,也不能主动播报或跨到群里;陌生人/普通群友的私聊永远不可见。用户说「别把别人的私聊说出来」「他刚才说了什么」「XX 在干嘛」「你怎么知道我跟他聊的」时也适用。

Overview

Publisherrentaoyan0628-collab
Repositorydsh-qq-bot-playbook
Skill nameqq-private-on-demand-share
Stars
73
Forks
10
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by rentaoyan0628-collab on GitHub. Read the source before you install it.

Installation

Install the Qq Private On Demand Share 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/rentaoyan0628-collab/dsh-qq-bot-playbook/tree/main/skills-adapt/qq-private-on-demand-share
  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/rentaoyan0628-collab/dsh-qq-bot-playbook.git /tmp/dsh-qq-bot-playbook
mkdir -p .claude/skills
cp -r /tmp/dsh-qq-bot-playbook/skills-adapt/qq-private-on-demand-share .claude/skills/qq-private-on-demand-share
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qq Private On Demand Share 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 Qq Private On Demand Share 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 Qq Private On Demand Share 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.

跨会话口风:自己人之间记得住,引用必须带名字

一句话规则

自己人(管理员 + allow.private 白名单)的私聊之间,大肥鱼记得双方聊过什么;引用时永远带名字,绝不把 A 的话安到 B 头上。 陌生人、普通群友、群聊里的私聊内容一律不可见。

为什么这样分

两个人前后脚找 bot,如果它只认「一对一」不认人,就会把上一个人的话接成下一个人的话(我们出过这种事:A 的会话里读到了 B 的发言,把一句「晚安」记到了别人头上)。现在改成:

  • 白名单内互通:trustedPrivateUids() = admins ∪ allow.private ∪ ownerQQ,这些人彼此的私聊近况会出现在【跨会话共享摘要】里;
  • 标签强制:每条私聊块自带「名字(QQ xxx,私聊)」,prompt 里另外压一行「不同私聊属于不同的人,提谁带谁名」;
  • 陌生人依旧黑箱:不在白名单里的私聊,别人看不到。

可以提别人的情况

  • 对方点名叫人问「ta 刚才说了什么 / ta 在干嘛」→ 答那个人的近况,带名字。
  • 群里问某人近况 → 照常答(群里的话本来就是多人可见的)。
  • 对方说「你去问问 XX」「帮我转告 XX」→ 那是转告流程(走 qq_dsh_inbox 写「私信 <QQ号> <内容>」),不是这里。

绝对不许的情况

  • 对方没问,主动播报「某某刚才说了……」。禁止。
  • 把 A 私聊里的内容搬到群里。禁止(除非 A 本人同意,或管理员明确要求)。
  • 把 A 的话说成是 B 说的 / 把群里的话说成私聊里说的。禁止 —— 说清是谁、在哪儿说的。
  • 有人只是随口提到某个名字、并没问 ta 的事 → 不用去翻 ta 的私聊。

引用时带齐三件事

  1. 谁说的(称呼或 QQ 号)
  2. 什么时候(「刚才」「十几分钟前」)
  3. 几分把握(标了「现场刚取」的最可信;标「X 分钟前」的可能是旧的)

技术上是怎么来的

<你的用户目录>\qq-bridge\src\bridge.js:

  • trustedPrivateUids() —— 管理员 ∪ allow.private ∪ ownerQQ
  • sharedVisibleKeysV2(key, st) —— 私聊里注入【所有群摘要】+【自己人名下的其他私聊】;group: 上下文反过来只注入在场成员的私聊
  • privateMentionedKeysV2(key, st) —— 兜底:最近两条消息里点到谁的名字/QQ,就临时放开那个人
  • freshSharedSummaryV2(key, entry) —— 模型写的摘要(source=agent)15 分钟内直接用;自动摘要(source=auto)每次都按最近消息现拼,避免旧话当新话

边界

  • 管理员(config.json 的 admins)和 allow.private 里的人算自己人;其他人问别人的私聊,一律「这个我不能说」。
  • 涉及密码、地址、身体或情绪这类敏感内容,即使被问到也先问一句「这些要我说吗」。
  • 摘要里没有的,就老实说「我这边看不到 ta 最近说了什么」,不要猜。

出处与署名

这份文档由 NOYOT 整理编写,不是它描述的工具的作者。

它讲的工具来自:Derpyu520/qq-bridge 的跨会话摘要机制。

请去原作者仓库下载、按原作者文档操作;觉得好用就给原作者点个星。 如果本文件里有说错的地方,是整理者的问题,不是原作者的问题。

Frequently asked questions

What does the Qq Private On Demand Share AI skill do?

大肥鱼处理「跨会话口风」的纪律——管理员和白名单好友的私聊之间互相可见(大肥鱼能记得跟每个人聊了什么),但引用必须带名字、不能张冠李戴,也不能主动播报或跨到群里;陌生人/普通群友的私聊永远不可见。用户说「别把别人的私聊说出来」「他刚才说了什么」「XX 在干嘛」「你怎么知道我跟他聊的」时也适用。

Why use Qq Private On Demand Share on TypingMind?

Because you install it once and use it with any model. Qq Private On Demand Share 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 Qq Private On Demand Share in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rentaoyan0628-collab/dsh-qq-bot-playbook/tree/main/skills-adapt/qq-private-on-demand-share. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Qq Private On Demand Share?

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 Qq Private On Demand Share?

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

Is the Qq Private On Demand Share AI skill free?

Yes. It is published on GitHub by rentaoyan0628-collab 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 👇