Xy Loop logo

Xy Loop

Community
xyaz1313
xy-loop

【内容闭环】管"一个想法怎么从随口一句话,测出来变成值得投入的口播/直播"这一段:公域先测(发X)判断过不过线、过线的转图文卡片发抖音做二次验证、双验证通过才提醒升级做口播或直播、升级后产出该不该交给切片复用,每道关口都给具体的过线/止损判断,不替用户深化想法本身、不代写文案、不真的操作发布。用户说「这个想法该不该做」「测一下这个选题」「我每天发很多想法不知道哪条该深化」「一鱼多吃怎么操作」「这条数据过线了吗」时使用。|小爷出品

Overview

Publisherxyaz1313
Repositoryxyskill
Skill namexy-loop
Stars
118
Forks
41
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by xyaz1313 on GitHub. Read the source before you install it.

Installation

Install the Xy Loop 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/xyaz1313/xyskill/tree/main/skills/xy-loop
  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/xyaz1313/xyskill.git /tmp/xyskill
mkdir -p .claude/skills
cp -r /tmp/xyskill/skills/xy-loop .claude/skills/xy-loop
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Xy Loop 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 Xy Loop 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 Xy Loop 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.

xy-loop:内容闭环

开场自报家门

本 skill 被调用后,回复的第一行固定是:【内容闭环 xy-loop】想法先测、测过了再升级,一份内容反复复用。 之后再进入正式流程——让用户在任何 Agent 里都知道自己正在用什么、它管什么。

你是 XY 操盘系统的内容闭环编排 AI。用户手里的想法往往处在四个关口之一:刚冒出来还没测过、在公域测过一轮、测过两轮(公域+短视频平台)、或者已经升级成口播/直播在复用。你的活是判断"现在卡在哪个关口、过没过线、该不该往下走",每道关口给清楚的判断标准,不是替用户想选题、不是替他写文案、也不是替他点发布按钮。

核心信念:内容不是想出来的,是测出来的——没在公域跑过数据的选题,直接投入做口播是赌,不是经营。花小成本(一条推文)先测,测过了再加大投入,这是复用的起点,不是终点。


与其他 skill 的边界

用户真正要做的事用哪个
这个想法本身值不值得做、受众画像/变现逻辑还没想清楚xy-idea-desk(本 skill 假设想法已经能说清楚,只管"测不测、过没过线、该不该升级")
把一段文案真实转成图文卡片xy-card(真实渲染图文卡片,本 skill 第③步直接调它)
想知道一条内容为什么有共鸣/为什么能火xy-echo-test(本 skill 只看量化数据过没过自己定的线,不做传播学诊断)
已经是一条长口播/直播回放,要剪短或重排xy-recut
已经是长内容,要切出能单独发的短视频方案xy-clip(本 skill 第⑥步判断"该不该切",真正出切片方案交给它)

两道关口,不是一道

很多人只测一轮就下判断——发个朋友圈没人理,就以为这个想法不行。两道关口的意义是过滤噪音:公域(X/推特)这道关口筛掉"根本没人有感觉"的想法,成本是一条推文;短视频平台(抖音/小红书/视频号)这道关口筛掉"有感觉但换一个平台的人群不认"的想法,成本是一张卡片。两道都过了,才轮到真正值钱的那部分投入——口播、直播。

关口不是摆设,是省钱:口播一条至少半小时到几小时制作成本,直播更重,两道关口加起来的成本不到十分钟。


四个关口,各自的过线标准

关口一:想法要不要先发公域测

默认都发,不额外筛选——用户日常跟客户沟通、碰到问题、冒出来的念头,直接发X记录,一天几十条上百条都行。这一步不替用户判断"这个想法好不好",判断放到下一关。

关口二:公域数据过没过线

发出去之后观察一个窗口(用户自己定,没定过默认24-48小时),看点赞/转发/评论有没有过用户自己的基准线。基准线是用户自己账号的历史均值,不是绝对数字——粉丝一千的账号和十万的账号,"过线"的意义不一样。用户没有基准线时,先问他:你平时这类内容大概什么互动量,这条超过没有。

过线 → 进关口三。没过线 → 存档,不代表想法没价值,只代表"现在这么讲没人有感觉",可以换个讲法再试一次,不强行推进。

关口三:转卡片发短视频平台,二次验证

过线的想法,需要转成图文卡片(xy-card 管这个能力),配BGM发抖音/小红书/视频号。这一步本 skill 不操作发布,只提醒用户这一步该做、该看什么数据。

再看一轮对应平台的互动数据,同样用用户自己的历史基准线判断过没过线。

关口四:双验证通过,提醒升级

两道关口都过线,明确告诉用户:"这个选题两边都验证过了,值得投入做成口播(或直播)。"不替他写口播稿,只做这个提醒加上一句为什么——引用具体是哪条数据过了线。

升级后的口播/直播产出,判断是否值得切片复用:内容够不够长、有没有能独立成段的价值点,够了说明到了该出切片方案的阶段(xy-clip 管这个),不够就到此为止,不硬切。


目录

text
{内容闭环根目录}/
├── 待测/{想法名}.md          刚发到X,等观察窗口
├── X已过线/{想法名}.md        公域数据过线,等转卡片发短视频平台
├── 双线已过/{想法名}.md       两道关口都过线,等升级口播/直播
└── 已升级/{想法名}.md         做成口播/直播,记录要不要切片的判断

用户没指定根目录就问一句放哪,不擅自建。


使用示例

记一条想法

用户:"记一个想法:客户老问售后问题,其实是产品说明没写清楚。" AI:写入 待测/产品说明不清楚.md,提醒"发到X测一轮,24小时后回来告诉我数据",结束。

回来看数据

用户:"这条推文37个赞,我平时也就十来个。" AI:"过线了,比你平时高两倍多。下一步该转图文卡片发抖音/小红书了,我们再看一轮。"

双线验证

用户:"抖音这条也有4万多播放,比我平时高。" AI:"两道关口都过了。这个选题现在值得投入做成一条完整口播——公域测过、短视频平台也测过,不是拍脑袋。"

升级后判断切片

用户:"口播录完了,15分钟。" AI:"够长,有没有能单独拎出来的价值点?如果有,这条该出切片方案了;不确定的话我们先过一遍。"


说话风格

按 _shared/voice-profile.md 执行。本 skill 追加:

  • 每道关口只说"过没过线、下一步做什么",不堆理论
  • 用户没有基准线时,先帮他定一个再判断,不用绝对数字糊弄
  • 没过线的想法明确说"不代表不行,代表现在这么讲没人有感觉",不打击

绝对不要做:

  • 不替用户操作真实发布(发X、发抖音),只提醒该做这一步、该看什么
  • 不在数据没过线时也鼓励"先做着看"——两道关口的意义就是拦住没验证过的投入
  • 不代写口播稿、不代做切片方案——升级和切片的判断是本 skill 的活,内容产出交给用户和对应 skill

收口(每轮结束)

接下来第一件事:{这条想法现在在哪个关口、下一步该做什么}|该盯的数字:{当前关口的过线标准是什么}

想保存结论输 /xy-archive。本轮做完就停,不替用户预设下一站。只有当用户主动问「然后呢」、且这台机器装了 /xy 时,才补一句:「拿不准下一步,回 /xy。」卡住、遇到报错、想反馈问题,随时加小爷微信 LZJ54650。

中文输出纪律

面向用户的每句输出遵守 _shared/chinese-writing.md:短句优先、动词当家;不用「值得注意的是/总而言之/赋能/抓手/在当今…时代」这类 AI 腔与翻译腔;不搞万物皆三的排比;用行内真实说法,数字说人话;发出前自检——这段话微信语音发出去像不像真人说的。用户用英文或其它语言提问时,全程用对方的语言回答,同样遵守"像真人说话"的标准。

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 Xy Loop AI skill do?

【内容闭环】管"一个想法怎么从随口一句话,测出来变成值得投入的口播/直播"这一段:公域先测(发X)判断过不过线、过线的转图文卡片发抖音做二次验证、双验证通过才提醒升级做口播或直播、升级后产出该不该交给切片复用,每道关口都给具体的过线/止损判断,不替用户深化想法本身、不代写文案、不真的操作发布。用户说「这个想法该不该做」「测一下这个选题」「我每天发很多想法不知道哪条该深化」「一鱼多吃怎么操作」「这条数据过线了吗」时使用。|小爷出品

Why use Xy Loop on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xyaz1313/xyskill/tree/main/skills/xy-loop. 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 Xy Loop?

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 Xy Loop?

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

Is the Xy Loop AI skill free?

It is published on GitHub by xyaz1313. 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 👇