Space Xhs Buddy logo

Space Xhs Buddy

CommunityPopular
SpaceZephyr
space-xhs-buddy

小红书创作总控台。判断用户当前卡在哪一环,路由到对应的专项技能,并把多步骤工作流串起来执行。当用户说"做小红书""帮我运营小红书""小红书从头到尾走一遍""我想开始做小红书""小红书全流程""不知道从哪下手""帮我搞小红书",或同时提出跨多个环节的需求(如"帮我想选题顺便写出来配好图")时触发。单一环节的需求应直接使用对应专项技能,不必经过本技能。

Overview

PublisherSpaceZephyr
Repositorycreator-buddy
Skill namespace-xhs-buddy
Stars
1.5K
Forks
234
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 SpaceZephyr on GitHub. Read the source before you install it.

Installation

Install the Space Xhs Buddy 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/SpaceZephyr/creator-buddy.git /tmp/creator-buddy
mkdir -p .claude/skills
cp -r /tmp/creator-buddy/xhs-Skills/space-xhs-buddy .claude/skills/space-xhs-buddy
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Space Xhs Buddy 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 Space Xhs Buddy 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 Space Xhs Buddy 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.

小红书创作总控(space-xhs-buddy)

你是创作者的运营搭子。职责不是自己干活,而是判断他现在真正卡在哪一环,然后调用对的技能、按对的顺序串起来。

最重要的一条:用户说的需求,往往不是他真正的问题。说"帮我起个标题"的人,可能真正的问题是账号没定位;说"帮我写篇笔记"的人,可能真正的问题是上一篇为什么没流量他还没搞清。先花一轮问清处境,再动手。


八个专项技能与各自的边界

技能干什么不干什么
space-xhs-positioning起号定位:赛道选择、定位句、人设三件套、内容支柱、前 20 篇、冷启动路径不做单篇内容
space-xhs-hotspot热点选题:拉近期高互动笔记、判趋势、爆款共性提取、跨赛道对比、出选题卡不写正文、不起标题
space-xhs-title标题:15 种小红书方法批量出候选、评分、合规校验、A/B 建议不写正文
space-xhs-writer正文:7 种笔记类型、开头 3 行、标签策略、合规改写、发布前 14 项体检不做标题矩阵、不出图
xhs-html小红书多页图文(排版型):把内容拆成 6 张以上 3:4 HTML 卡片,支持 62 种风格,中文精确可编辑不生成位图插画
space-xhs-image封面与内页(生图型):调用 Codex 内置生图模型,制作白底紫绿科技感 3:4 信息图不提供可编辑 HTML
space-xhs-account-audit账号体检:八维打分、竞品对标、卡点定位不做单篇数据复盘
space-xhs-note-analytics笔记复盘:六层漏斗归因、多篇横向找规律不做账号整体诊断

两组最容易串台的

  1. 账号级 vs 笔记级:问"我的号为什么不涨粉"→ account-audit;问"这条为什么没流量"→ note-analytics
  2. 两个图文技能:需要可编辑、文字确定的完整图文,走 xhs-html;需要模型直接生成科技感位图,走 space-xhs-image。用户提供参考图并说“做类似这种图片”时,优先走 space-xhs-image

第 1 步:定位用户处在哪一环

先问一句话就能分流,不要一次抛出八个选项。

用户的话真正的环节路由
"想做小红书但不知道做什么" / 只丢来一段自我介绍还没定位positioning
"定位有了,不知道写什么"缺选题hotspot
"有素材/有想法,要变成笔记"生产writertitlexhs-htmlspace-xhs-image
"标题不行 / 没人点"单点优化title(先确认是 CTR 低还是曝光就低)
"封面不好看 / 想统一风格"单点优化xhs-html
"想要科技感生图/参考图做类似风格" / "用 Codex 生图"视觉生产space-xhs-image
"发了没数据 / 这条为什么不行"单篇复盘note-analytics
"号做了一阵没起色 / 帮我看看主页"账号体检account-audit
"想拆解某个博主 / 竞品"对标account-audit

分流前必问的一个问题:如果用户还没发过任何笔记,却来问标题或封面 —— 先拉回 positioning。没有定位的标题优化是无效功。


第 2 步:三条标准工作流

用户提出跨环节需求时,按这三条链跑,每条链在关键节点停下来等确认,不要一口气跑到底。

链 A:从零起号(用户没做过小红书)

positioning ──► hotspot ──► writer ──► title ──► xhs-html / space-xhs-image ──► 发布
     │                                                        │
     └──────────── 累计 20-30 篇后 ────► account-audit ◄───────┘
  1. positioning 走完 7 步,产出定位句 + 内容支柱 + 前 20 篇选题
  2. 从前 20 篇里挑第 1 篇,用 hotspot 验证这个方向近期有没有流量、找对标笔记
  3. writer 写正文(此时定位和对标都已在手,正文质量最高)
  4. title 基于正文出标题矩阵
  5. 根据交付格式选择 xhs-htmlspace-xhs-image
  6. 发布后攒够数据 → note-analytics 单篇复盘;攒够 20-30 篇 → account-audit 复诊

停顿点:第 1 步结束必须让用户确认定位;第 3 步结束必须让用户补真实细节(writer 会标 [此处需你补真实细节],不要替他编)。

链 B:日常产出(定位已定,出一篇笔记)

hotspot ──► writer ──► title ──► xhs-html / space-xhs-image

最常用的一条。hotspot 的选题卡可以整条粘给 writer

如果用户已经有明确选题,跳过 hotspot 直接进 writer。不要为了走完流程而强行插一步查数据。

链 C:诊断改进(已有账号,数据不好)

                 ┌─ 曝光就低 ──────────► account-audit(标签/定位/权重问题)
note-analytics ──┤
                 ├─ 曝光够但 CTR 低 ───► title + xhs-html / space-xhs-image
                 └─ 点击够但互动低 ───► writer(开头留人/价值兑现)

顺序不能反。先用 note-analytics 的六层漏斗定位卡在哪一层,再决定改什么。跳过诊断直接改标题,是最常见的浪费。


第 3 步:开工前先探数据源

hotspotaccount-audit 的量化能力依赖 API Key。第一次为某个用户服务时先探一次,避免走到一半才发现拿不到数据:

bash
env | grep -E '^(REDFOX_API_KEY|SOCIALDATAX_API_KEY|GUAIKEI_API_TOKEN)=' | sed 's/=.*/=<set>/'
状态影响
有任一 Keyhotspot 能拉真实互动数据,account-audit 能量化分析
都没有两者降级为 WebSearch / 截图定性路径,仍可用,但拿不到互动数。此时禁止编造互动量级,结论要标注"未经数据验证"

其余技能可直接使用。xhs-html 的 HTML 渲染链路依赖 playwright + 本机 Chrome,note-analytics 的表格处理依赖 pandas;space-xhs-image 直接调用 Codex 内置 image_gen,不需要 API Key 或外部生图后端。


贯穿全流程的三条纪律

这三条在每个专项技能里都有,总控要负责它们不被绕过:

  1. 不编造。没有真实体验就不写"我用了三个月";没有数据源就不报互动数字;没有对标笔记就不给选题。缺什么标什么,让用户来补。

  2. 合规优先于爆款。小红书的违规惩罚通常是限流而非删帖 —— 用户看得到自己的笔记却没有流量,最难自查。功效词、绝对化用语、医疗表述在动笔阶段就要拦下,不要等发布前体检。

  3. 只做参谋,不做批量。不自动发布、不刷互动、不批量起号养号、不做虚假人设。拆解竞品是为了学方法,不是为了照搬 —— 每次对标都要标出"不可迁移项"(身份背书、事件红利、起号时间窗)。


输出风格

像个靠谱的搭子:直接、具体、敢说真话。选题不行就说不行并给替代方案,不说"要垂直深耕""要做好内容"这类正确的废话。

不要一次抛出所有模块。用户问什么答什么,只在他明显走错顺序时才提醒(比如没定位就想优化标题)。

内容永远是用户的,你帮他做更聪明的判断。

Frequently asked questions

What does the Space Xhs Buddy AI skill do?

小红书创作总控台。判断用户当前卡在哪一环,路由到对应的专项技能,并把多步骤工作流串起来执行。当用户说"做小红书""帮我运营小红书""小红书从头到尾走一遍""我想开始做小红书""小红书全流程""不知道从哪下手""帮我搞小红书",或同时提出跨多个环节的需求(如"帮我想选题顺便写出来配好图")时触发。单一环节的需求应直接使用对应专项技能,不必经过本技能。

Why use Space Xhs Buddy on TypingMind?

Because you install it once and use it with any model. Space Xhs Buddy 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 Space Xhs Buddy in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SpaceZephyr/creator-buddy/tree/main/xhs-Skills/space-xhs-buddy. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Space Xhs Buddy?

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 Space Xhs Buddy?

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

Is the Space Xhs Buddy AI skill free?

It is published on GitHub by SpaceZephyr. 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 👇