Qq Admin Relay logo

Qq Admin Relay

Community
rentaoyan0628-collab
qq-admin-relay

QQ 管理员需要把任务转交给 DSH/本机 worker 时使用:用户说「转告dsh」「帮我放进传话箱」「放行传话箱」「让dsh做」,或者要求唱歌/点歌/用 ACE 生成歌曲(不是普通说话语音)时,必须用 qq_dsh_inbox 写入传话箱,不要自己直接执行。要求「去私信某个人」「帮我跟某某说」时也用 qq_dsh_inbox,text 写成「私信 <QQ号> <内容>」由桥接直接代发。私聊任务回私聊,群聊任务回群聊。

Overview

Publisherrentaoyan0628-collab
Repositorydsh-qq-bot-playbook
Skill nameqq-admin-relay
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 Admin Relay 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-admin-relay
  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-admin-relay .claude/skills/qq-admin-relay
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qq Admin Relay 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 Admin Relay 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 Admin Relay 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.

管理员转交 / 点歌

触发条件

管理员(owner 或 admin 列表内的人)说下面这类话,就走传话箱:

  • 「转告 dsh……」
  • 「帮我放进传话箱」「放行传话箱」「交给 dsh 做」
  • 「让 dsh 去……」
  • 「唱首歌」「点歌」「用 ACE 生成一首歌」「生成唱歌」
  • 任何需要本机 ACE、worker、DSH 主会话才能完成的事

普通说话语音(「发条语音」「说句话」)仍然用 qq_speak,不要走传话箱。

代发私信(替本人给别人发消息)

触发:「你去私信一下 X」「帮我跟 X 说……」「给 X 发条消息说……」——对象是另一个好友,不是回当前会话。

仍然用 qq_dsh_inbox,但 text 写成一行 私信 <QQ号> <内容>:

text
私信 100000002 晚上一起吃饭吗,六点老地方。

桥接看到 私信 <5~12 位 QQ 号> 开头,会直接代发出去(不再转给 DSH);返回里带 relay 字段就说明已经发出。发完回一句「发了」即可。

规矩:

  1. 不要用 qq_send_private_message 发给别的会话——agent token 是按会话签发的,跨会话必失败(报「agent token 无效」)。这是它以前做不成这件事的真正原因。
  2. 发起人必须是管理员或 allow.private 里的白名单好友;白名单好友不受"刚说过话"的窗口限制(2026-10-24 放宽,群里直接可发)。只有「管理员但不在白名单」的号才需要 15 分钟内本人发过言。被拒时桥接会返回理由,照抄理由回给对方即可。
  3. 目标必须是 allow.private 里的好友;不在白名单就直说「他没在白名单里」。
  4. 内容按原话写,不要加戏;单条最多 500 字。
  5. 发完不复述内容、不编造对方的回复。

必须用的工具

调用当前会话的 qq_dsh_inbox:

text
key:   当前会话 key(private:100000001 或 group:100000003)
token: 本轮唤醒提示里的【会话令牌】
text:  结构化任务,见下

text 建议写成:

text
【管理员转交】
来源:<private:... / group:...>
管理员:<昵称/QQ>
要求:<原话,不要改写关键参数>
类型:<唱歌/点歌/改配置/其他>
发回:<同一个 private 或 group>

唱歌类要额外写清楚:

text
类型:ACE 唱歌任务
要求:用 ACE 生成,成品按管理员要求裁剪,转 128kbps MP3
发回:<当前会话 key>

行为规则

  1. 只写传话箱,不要自己生成歌曲:不要调 ACE、不要调 GPT-SoVITS 唱歌、不要假装已经生成。
  2. 写完后短回一句:「已经放进传话箱了,worker 会处理。」不要复述内部实现。
  3. 来源即回传目标:私聊来的任务回私聊,群聊来的任务回群聊;不要把群聊任务私发,也不要把私聊任务发群。
  4. 非管理员说这些,统一拒绝:「这个要管理员权限哦。」
  5. 管理员说「转告 dsh」但没有给内容时,先问一句「要转告什么?」;有内容就直接写,不要反复确认。
  6. 不要把「唱歌」当普通语音;唱歌任务只走传话箱 + worker。

回执纪律(2026-10-25 加严)

管理员提过「转给 DSH 的回执时有时无」,所以:

  1. 必须真的调用 qq_dsh_inbox,不能只嘴上说「已转达」。
  2. 返回 ok: true 才能说转成了;回执里的 receipt 带 id=inbox-…,把这个 id 报给管理员(他据此核对送达)。
  3. 返回 ok: false 或工具报错 → 直说「没转成 + 原因」,不要含糊带过,也不要编成功。
  4. 转达成功后回一句短的即可,例如:「转到了,回执 id inbox-179…」。不用复述内容。
  5. 管理员问「到底转了没有」时,如果当时没留 id,就说「我不确定,重发一次」并重新调用工具——宁重重一次,别猜。

示例

管理员私聊:「转告 dsh,把 GPT 语音语速调到 0.85」

→ qq_dsh_inbox({ key: "private:100000001", token, text: "【管理员转交】\n来源:private:100000001\n管理员:年银滔\n要求:把 GPT 语音语速调到 0.85\n类型:改配置\n发回:private:100000001" })

管理员群里:「大肥鱼唱首摇篮曲」

→ qq_dsh_inbox({ key: "group:100000003", token, text: "【管理员转交】\n来源:group:100000003\n管理员:<昵称>\n要求:唱一首摇篮曲,20 秒,ACE 直出,128kbps MP3\n类型:ACE 唱歌任务\n发回:group:100000003" })


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 的传话箱与代发私信通道。

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 Admin Relay AI skill do?

QQ 管理员需要把任务转交给 DSH/本机 worker 时使用:用户说「转告dsh」「帮我放进传话箱」「放行传话箱」「让dsh做」,或者要求唱歌/点歌/用 ACE 生成歌曲(不是普通说话语音)时,必须用 qq_dsh_inbox 写入传话箱,不要自己直接执行。要求「去私信某个人」「帮我跟某某说」时也用 qq_dsh_inbox,text 写成「私信 <QQ号> <内容>」由桥接直接代发。私聊任务回私聊,群聊任务回群聊。

Why use Qq Admin Relay on TypingMind?

Because you install it once and use it with any model. Qq Admin Relay 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 Admin Relay 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-admin-relay. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Qq Admin Relay?

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 Admin Relay?

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

Is the Qq Admin Relay 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 👇