Video Chapters logo

Video Chapters

Community
JimLiu
video-chapters

用户要给视频分章节、加章节或时间轴目录、按作者给的时间大纲生成章节,或调整章节的粗细时用:在自然的话题转换处分章,每章一个标题和一句话摘要,写进视频的章节。需要视频的转写。不用于只想在简介里列出已有章节(用起标题与写简介),也不用于给文章分节。

Overview

PublisherJimLiu
Repositorybaocut
Skill namevideo-chapters
Stars
687
Forks
57
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 JimLiu on GitHub. Read the source before you install it.

Installation

Install the Video Chapters 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/JimLiu/baocut/tree/main/skills/baocut/built-in-skills/video-chapters
  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/JimLiu/baocut.git /tmp/baocut
mkdir -p .claude/skills
cp -r /tmp/baocut/skills/baocut/built-in-skills/video-chapters .claude/skills/video-chapters
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Video Chapters 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 Video Chapters 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 Video Chapters 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.

分章节

章节是给观众跳着看用的:拖进度条的人看一眼章节名,就知道要去哪一段;看过的人想回头找某个地方,也靠它。所以章节的标题要说清这一段讲什么,起点要落在话题真正开始的地方,一个章节对应一个话题。

最容易做坏的样子有两种。一种是按时间平均切:每五分钟一章,起点落在一句话的中间,标题是「第一部分」「继续讨论」,观众看了等于没看。另一种是标题太像总结:一章一句长话,章节列表反而读不动。章节名是路标,不是摘要;摘要另有一句话的位置。

1. 取材料

  1. 用 videos_inspect 看视频:时长、已有的章节(chapters)、文档。没有转写(kind 为 speech 的文档)时先转写,告诉用户转写在进行。从链接导入的素材另有 assets[].source:chapters 是作者的章节(平台给的结构化章节,或从简介里的时间戳大纲解析出来的),没有时是 [];description 是截断的简介。
  2. 带时间码的文稿:export(kind transcript、format md、timestamps true;有几份文稿时按它列出的候选用 documentId 指定),jobs_inspect 等到 completed,读 outputs 里的文件。它按段落给出剪辑后时间线上的时间,章节的时间就取段落开头的这个时间码,不要自己估算。
  3. 视频已经有章节时,先问用户是要替换、调整还是保留;用户只说「加章节」而已有的章节是新的,不要覆盖。

2. 有作者章节或用户给了大纲时

作者自己分过的章节通常比你分的更贴近他的意图,照它来,不自己分,也不手工对时间。来源素材自带章节(assets[].source.chapters 不为空),或用户贴来一份带时间的大纲(0:00 开场、1:02:03 问答 这类)时,用 chapters_adopt:

  • 作者章节:给 video(素材不止一个时给 asset,有几份转写时给 document)。用户贴的大纲:给 outline,可以是 [{ at, title }],也可以是贴来的原文。不确定时先带 dryRun 看回执,再正式写。
  • 它把每一条吸到文稿里最近的段落或句子起点(段落优先,其次句子、字幕条、词),清洗标题后整份写进视频的章节(替换已有的;已有章节要先按第 1 步问过用户)。
  • 读回执的 sourceChapters:entries 共几条;matched 吸到了起点;ambiguous 附近有几个起点、取了离作者时间最近的那个(同样近取靠后的);snapped 时间挪动过;unanchored 对不上、保留了原来的时间。rows 逐条给标题、写入的时间 at、原来的时间 sourceAt 与状态;带 offTimeline 的条目对应的地方不在时间线上(比如剪掉了)。交付时说清对上几条,把 ambiguous、unanchored、offTimeline 的条目逐条列给用户:这些是他要自己看一眼的地方。
  • 返回 NO_SOURCE_CHAPTERS:素材没有作者章节,按下面的做法自己分。返回 ASSET_NOT_PLACED:素材不在时间线上,先放上去。
  • 用户要你自己写的章节,或想要和作者大纲不同的粗细时,才走下面的做法自己分,作者的大纲当参考:转写和它吻合的地方沿用它的分界和标题(保留作者用的语言与措辞),只在转写明显不同的地方增、并、删章;大纲的时间只是大致的,章节的起点仍取文稿里段落的时间码。

3. 分几章

按粗细定一个大致的目标章数,不硬凑:

粗细大约多长一章
粗约 10 分钟
适中(默认)约 5 分钟
细约 2.5 分钟

目标章数 = 时长 ÷ 每章时长,取整;至少 2 章,最多 20 章,超过一小时的录音上限按每小时 20 章放大。有作者大纲当参考、用户又没指定粗细时,目标章数取大纲的条数。话题真正的转换比这个少时,少分几章没关系:目标章数是个大概,不是指标。

4. 怎么分

动手前先通读文稿,列出话题在哪里转换:说话人换了题目、从问题转到做法、从一个案例转到下一个。章节就落在这些地方。

  • 每章从一段话的开头开始;时间取文稿里那一段的时间码。不编造时间,不把章节放在一句话的中间。
  • 第一章通常从 0 秒开始。
  • 每章一个标题和一句话的摘要(不超过约 20 个词,说清这一章讨论什么)。标题是观众扫一眼就懂的路标,用这一段的内容本身,不用「第一部分」「继续」「其他」这类说了等于没说的词;摘要补一句这一章具体讲到什么。
  • 标题和摘要不能为空,彼此不同,风格一致;用转写的语言写,用户要别的语言时才换。
  • 录音很长时分几部分读:每部分先列出话题单元(各自的起点段落、标题和摘要),再把它们合成最终的章节。单元比目标章数多时,把属于同一个更大话题的相邻单元合成一章,起点取合并后第一个单元的起点,标题和摘要覆盖合并后的整段;分部分的接缝处尤其要合并,那里一个话题常被人为切开。不是第一部分时,开头可能接着上一部分的话题,不必在这一部分的第一段强加一章。

对比一下(只是示意):

不好:05:00 第二部分 / 10:00 继续讨论模型 / 15:00 其他

好:04:37 为什么蒸馏后效果掉得厉害 / 11:02 混合方案怎么配 / 16:48 上线后的三个坑

后一种每个起点都落在话题开始的那一段,标题看一眼就知道要不要跳过去。

5. 写进视频

用 edits_apply 的 setChapters 一次写入整份章节列表(at 是上面取到的秒数,按时间严格递增;title、summary 照写)。只改一两章时用 upsertChapter 或 removeChapter。章节固定在时间线的时刻上:剪口播(addCuts、接受剪辑建议、恢复剪口)会让章节跟着内容走,别的剪辑(移动、删除片段、波纹删除)不会,这类剪辑改了时长时提醒用户章节可能要重新对一遍。

6. 要避免的

  • 不要按时间平均切,不要把起点放在一句话中间,不要自己估算时间。
  • 标题不要写成「第一部分」「继续」「其他」,也不要写成一整句摘要。
  • 素材有作者章节时不要自己重分;用户已有章节时不要不问就覆盖。
  • 不要硬凑目标章数。

7. 交付

  • 列出写进去的章节:时间(时:分:秒,不到一小时写分:秒)、标题、摘要。
  • 说明用的是作者的大纲还是自己分的,粗细与章数。用了作者大纲时报吸附统计:共几条、对上几条;ambiguous、unanchored、offTimeline 的条目逐条列出。
  • 分章失败不影响转写和其他结果:如实说明原因,最多重试一次,不反复重试。

Frequently asked questions

What does the Video Chapters AI skill do?

用户要给视频分章节、加章节或时间轴目录、按作者给的时间大纲生成章节,或调整章节的粗细时用:在自然的话题转换处分章,每章一个标题和一句话摘要,写进视频的章节。需要视频的转写。不用于只想在简介里列出已有章节(用起标题与写简介),也不用于给文章分节。

Why use Video Chapters on TypingMind?

Because you install it once and use it with any model. Video Chapters 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 Video Chapters in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JimLiu/baocut/tree/main/skills/baocut/built-in-skills/video-chapters. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Video Chapters?

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 Video Chapters?

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

Is the Video Chapters AI skill free?

It is published on GitHub by JimLiu. 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 👇