Quick Tweet logo

Quick Tweet

Community
bozhouDev
quick-tweet

快速信息推文 — 用户丢过来一条推文链接、新闻、开源项目、产品动态等素材,快速消化内容,写一条信息推文,判断该引用转发还是原创发布,确认后通过 xurl 直接发送。当用户说"帮我转发这个"、"这个发一条推"、"帮我分享这个"、"这条推翻译一下发出去"、"写个推发出去"并附带了链接或素材时触发。也适用于用户贴了一段英文内容想快速中文转发的场景。

Overview

PublisherbozhouDev
Repositorybozhou-skills
Skill namequick-tweet
Stars
78
Forks
7
Bundled files
Instructions only
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 bozhouDev on GitHub. Read the source before you install it.

Installation

Install the Quick Tweet 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/bozhouDev/bozhou-skills/tree/main/quick-tweet
  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/bozhouDev/bozhou-skills.git /tmp/bozhou-skills
mkdir -p .claude/skills
cp -r /tmp/bozhou-skills/quick-tweet .claude/skills/quick-tweet
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Quick Tweet 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 Quick Tweet 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 Quick Tweet 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.

快速信息推文

把外部素材(推文、新闻、开源项目、产品更新)快速转化为一条可发布的中文推文。

受众

泊舟的读者主要是不懂技术的小白和 AI 初学者 — 他们对 AI 好奇、想用起来,但不写代码、不懂架构。写推文时要站在他们的角度:

  • 技术概念必须用一句大白话解释清楚,不能假设读者知道
  • 重点说"这东西能干嘛、跟普通人有什么关系",而不是底层技术细节
  • 专业术语第一次出现时用括号或逗号补一句解释,比如"MCP(一种让 AI 工具互相连接的协议)"
  • 如果一个更新只对开发者有意义、普通人用不上,要在推文里说清楚这一点,别让小白觉得自己该懂但不懂

这个 skill 做什么

用户给你一个素材(推文链接、新闻截图、项目地址、一段文字),你需要:

  1. 搞清楚这个东西到底是什么、有什么用
  2. 用泊舟的风格写一条中文推文,确保 AI 小白也能看懂
  3. 判断应该引用转发还是原创发布
  4. 用户确认后,能直接发的就直接发

和 tweet-writer 的区别

tweet-writer 适合原创观点、深度内容、框架型认知等需要琢磨的推文。 这个 skill 是信息转译快车道 — 核心是把英文/外部信息快速转化成中文读者能看懂、想看的推文。

写作风格

语气和用词遵循 bozhou-writing-style skill 的规范 — 泊舟自己的风格,不模仿别人。

写之前先读一下 bozhou-writing-style 的 SKILL.md,确保语气、禁用词、句式习惯都对。

信息推文的结构

参考歸藏(@op7418)的信息推文结构,他做科技信息转译的结构非常高效:

开头:钩子 — 第一句话决定读者会不会继续看

遵循 CLAUDE.md 中的钩子写作指南。信息推文的钩子通常是反差型或场景型:

  • 直接点名主角 + 发生了什么,不用"最近发现..."、"分享一下..."这种空话铺垫
  • 如果有反直觉的事实,直接放第一句
好的结构:
"Claude Code 也能使用 Computer Use 了"(直接说事)
"4B 参数的小模型,在长上下文跑分上干翻了 235B 级别的方案"(反差钩子)

不好的结构:
"最近看到一个很有意思的更新..."
"分享一个好消息..."

正文:说清楚价值,列出能干嘛

  1. 一句话说是什么 — 让读者知道这东西解决什么问题
  2. 列举用途(可选)— 用"你可以用它..."或冒号后换行列点,给读者具体画面
  3. 给个判断(可选)— 基于自己的使用经验或理解,说说这个东西好在哪、差在哪

结尾:链接或引用放最后

  • 如果有原推/原文链接,放在最后一行
  • 如果有截图/视频,配在推文里

长度控制

信息推文 100-200 字左右。不需要面面俱到,抓住最核心的 1-2 个亮点就够了。超过 280 字就考虑删减。

工作流程

第一步:理解素材

用户给的素材可能是:

  • 一条推文链接 → 用 xurl read 读取内容
  • 一个 URL → 用 WebFetch 抓取
  • 一段文字/截图 → 直接阅读

把事情搞清楚:这是什么、谁做的、核心亮点是什么、跟我们的读者有什么关系。

第二步:判断发布方式

引用转发(Quote Tweet):

  • 素材本身是一条推文
  • 且原推有足够的信息量值得读者点进去看
  • 这种情况写一条点评/翻译,让用户自己在 X 上操作引用转发

原创发布:

  • 素材不是推文(新闻、项目、公告等)
  • 或者原推信息量不大,你的推文已经涵盖了全部要点
  • 这种情况确认后直接用 xurl post 发出去

告诉用户你的判断和理由,让用户决定。

第三步:写推文

写完草稿后自检:

  • 钩子过关吗?第一句话能不能被看完?看完后想不想看下一段?
  • 有没有说清楚这东西的实际价值?小白能看懂吗?
  • 长度合适吗?信息推文不需要太长
  • 有没有用了总结式 AI 转场?禁用"简单说"、"说白了"、"换句话说"、"这意味着",能删就删,直接进入判断或例子
  • 有没有触犯 bozhou-writing-style 的禁止清单?(破折号、"众所周知"、emoji 堆砌等)

把草稿给用户看,等确认或修改意见。

第四步:发布

如果是原创推文(用户确认后):

bash
xurl post '推文内容'

如果推文带图片,先上传再发:

bash
xurl media upload --media-type image/jpeg --category tweet_image photo.jpg
xurl post '推文内容' --media-id MEDIA_ID

如果是引用推文: 把写好的推文文案给用户,告诉他: "这条适合引用转发,原推链接是 xxx,你在 X 上引用这条推文,把文案贴进去就行。"

或者如果能拿到原推 ID,也可以用:

bash
xurl quote TWEET_ID '推文内容'

第五步:归档

发布成功后,将推文写入 创作/推文/{YYYY}/{MM}.md。

格式:

markdown
## {YYYY-MM-DD}

{推文正文}

如果是引用推文,在正文前加一行:

markdown
> 引用:{原推链接或摘要}

如果该日期下已有内容,追加在后面。文件不存在则创建,标题为 # {YYYY-MM} 推文记录。

注意事项

  • 不要编造信息。素材里没提到的数据、功能不要瞎加
  • 翻译英文内容时意译而非直译,用中文读者习惯的表达
  • 如果素材信息量太少写不出有价值的推文,直接告诉用户"这个素材信息量不够,建议补充 xxx"
  • 引用推文的判断要明确告知用户,不要默默选了一种方式
  • 用 xurl 发推时注意单引号包裹内容,内容中的单引号要转义

Frequently asked questions

What does the Quick Tweet AI skill do?

快速信息推文 — 用户丢过来一条推文链接、新闻、开源项目、产品动态等素材,快速消化内容,写一条信息推文,判断该引用转发还是原创发布,确认后通过 xurl 直接发送。当用户说"帮我转发这个"、"这个发一条推"、"帮我分享这个"、"这条推翻译一下发出去"、"写个推发出去"并附带了链接或素材时触发。也适用于用户贴了一段英文内容想快速中文转发的场景。

Why use Quick Tweet on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bozhouDev/bozhou-skills/tree/main/quick-tweet. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Quick Tweet?

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 Quick Tweet?

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

Is the Quick Tweet AI skill free?

It is published on GitHub by bozhouDev. Check the repository for licensing terms. 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 👇