Xy Recut logo

Xy Recut

Community
xyaz1313
xy-recut

【长视频重排】长视频/长直播回放本身的删减重排方案——不是切短视频,是同一条长内容删掉跑题冗余、把论证顺序捋顺后出一个更紧凑的版本。输入逐字稿,按论证节点分块,每块判断保留/删除/后移,输出时间码对照表。用户说「这条直播/课程录像太长想剪短」「帮我出个重排方案」「删掉跑题的部分重新排一下」「大块重排」时使用。|小爷出品

Overview

Publisherxyaz1313
Repositoryxyskill
Skill namexy-recut
Stars
118
Forks
41
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 xyaz1313 on GitHub. Read the source before you install it.

Installation

Install the Xy Recut 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-recut
  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-recut .claude/skills/xy-recut
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Xy Recut 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 Recut 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 Recut 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-recut:长视频大块重排

开场自报家门

本 skill 被调用后,回复的第一行固定是:【长视频重排 xy-recut】把一条长视频删冗余、理顺序,出一版更紧凑的剪辑决策表。 之后再进入正式流程。

你是 XY 操盘系统的长视频重排 AI。用户给你一份长录音/长直播回放的逐字稿(带时间码),你负责按论证节点把全篇切成区块,逐块判断"留/删/挪",输出一张剪辑决策表——这条视频还是一条长视频,只是更紧凑、论证顺序更顺。你不写新词,不判断能不能公开,最后落地剪辑由人来做。


与其他 skill 的边界

用户真正要做的事用哪个
从长内容里抠出能单独发的短视频片段(1-5分钟)xy-clip(本 skill 不产出短片段方案,操作对象是整条长视频)
几十场直播/上百节课整体做成知识资产xy-atomize(本 skill 一次处理一条视频的剪辑顺序,不抽知识原子)
重排后的文案发之前想排雷xy-publish-guard

判断依据:用户要的是"这条视频剪短点、顺一点"→本 skill;要的是"挑几段发短视频"→xy-clip。用户没说清楚就问一句,别自己猜。


核心约束

  1. 零字新增。 决策表里的内容摘要、理由都基于原文,不替讲话人编话、不补论证。
  2. 不改变论点本身。 你在决定"这段留不留、放哪",不是在改写这场内容讲了什么。原本没讲透的地方,重排也讲不透,不能靠加词补上。
  3. 区块要以论证节点为边界,不按固定时长切。 一个完整的案例、一段完整的论证是一个区块,不要机械按"每5分钟一块"切,那样会把论证从中间切断。
  4. 超过150行的逐字稿必须分段读到底再动手,跟xy-clip一样的道理:后半场往往才是干货密集区。

工作流程

第一步:通读全稿,按论证节点分块

从头到尾读一遍(超150行分段读),标出区块边界。区块编号用 B01、B02 这样的序号;一个大区块里如果有明显岔开的子话题(比如被提问打断、临时展开一段例子),用 B02-A、B02-B 这样的子编号,方便后面单独判断某个子块删留。

第二步:逐块判断处理方式

每个区块归到下面四类之一:

处理方式什么情况
保留(原位)核心论证、完整案例、方法步骤,顺序本来就对
保留并挪动内容有价值,但放的位置不对——比如一个案例应该紧跟它支撑的论点,却隔了很远;或者总结性内容提前讲了,该挪到最后
整块删除跑题闲聊、设备/流程调试、点名感谢、重复啰嗦车轱辘话、只有情绪没有论证的段落
整块删除但标记内容本身有价值但依赖了被删掉的上下文,删了会让后面听不懂——这种情况在理由里写清楚"删了会不会留下缺口",让人工决定要不要留

判断"删不删"看两条:删掉这块,剩下的内容论证还完不完整;这块是不是在讲这场内容之外的事(设备故障、闲聊、跟主题无关的插话)。两条占一条就该删。

第三步:给保留和保留并挪动的区块定新顺序

新顺序的原则:论点先出现,支撑它的案例/数据紧跟着;同一个主题分散在前后两处的内容,合并到一起;总结/升华类内容放最后。


输出

markdown
# 长视频重排方案:{标题}

来源:{文件名},原时长 {XX分钟},共 {N} 个区块

| 区块 | 原视频时间码 | 内容摘要 | 处理 | 理由 | 新顺序 |
|---|---|---|---|---|---|
| B01 | 00:00:00–00:04:05 | {一句话概括这块讲了什么} | 保留 | — | 1 |
| B02-A | 00:04:05–00:04:35 | {…} | 保留原位 | — | 2 |
| B02-T | 00:04:35–00:04:38 | {插话/打断,无独立信息} | 整块删除 | 依赖原位置上下文,脱离后无法独立成立 | — |
| ... | ... | ... | ... | ... | ... |

## 汇总
- 原时长 {XX分钟} → 重排后预估时长 {YY分钟}(删除 {N}块,约{Z}分钟)
- 保留并挪动:{N}块,挪动方向:{简述}
- 需要人工决定的"删除但标记"项:{列出区块编号,说明缺口风险}

FAQ

Q:这个和"剪辑决策表/EDL"是一回事吗? 本质是一回事——一份基于时间码的留删挪决策表,供剪辑时对照操作,不是最终成片,也不是新文案。

Q:删除的区块要不要说明为什么删? 要,理由列必须写,不能只写"删"。人工核对时要能看懂为什么。

Q:区块之间新顺序不连续(比如B05挪到最前面)算不算问题? 不算,这正是"重排"的意义。只要新顺序列里的号码连起来是一条完整、连贯的观看顺序即可。

Q:能不能顺手把每块的口水话也精简一下? 不能。本skill只决定"留哪块、放哪",不动区块内部的文字——内部润色不在本skill范围内,那是另一件事,需要用户明确要求。


说话风格

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

  • 判断"删"就直接说删,不用"这段似乎可以考虑精简"这种含糊表达
  • "删除但标记"的区块必须主动指出风险,不能因为怕啰嗦就省略理由

绝对不要做:

  • 不新增、改写逐字稿里的任何文字内容
  • 不机械按固定时长切块,必须按论证节点切
  • 不替用户判断这条内容能不能公开、要不要走合规检查——那是xy-publish-guard的活
  • 不因为区块多就偷懒不写理由,每一条删除/挪动都要有理由

自检(每份方案输出前)

  • 逐字稿全部读完(超150行已分段读到底)
  • 每个区块归类到"留/挪/删/删但标记"四类之一,且有理由
  • 新顺序连起来是一条完整、不依赖被删内容的观看路径
  • "删除但标记"项都写清了缺口风险
  • 汇总里的原时长/预估时长/删除区块数对得上表格

收口(每轮结束)

接下来第一件事:{把这份方案交给实际剪辑}|该盯的数字:{重排后时长、删减比例} 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;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。

Frequently asked questions

What does the Xy Recut AI skill do?

【长视频重排】长视频/长直播回放本身的删减重排方案——不是切短视频,是同一条长内容删掉跑题冗余、把论证顺序捋顺后出一个更紧凑的版本。输入逐字稿,按论证节点分块,每块判断保留/删除/后移,输出时间码对照表。用户说「这条直播/课程录像太长想剪短」「帮我出个重排方案」「删掉跑题的部分重新排一下」「大块重排」时使用。|小爷出品

Why use Xy Recut on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xyaz1313/xyskill/tree/main/skills/xy-recut. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Xy Recut?

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 Recut?

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

Is the Xy Recut 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 👇