Index of every page on this site: llms.txt
All skills
wangzan101 avatar

/content-transcribe

@0c258ac
by WangZanwangzan101/mika9.2k stars
2,081
Run it yourself

把视频、播客、文章整理成文字:摘要、分章节、摘引文或改写成文章

  • 2 files
  • 3.7 KB
  • Updated 4 days ago
  • GitHub
Use this Skill: https://skilld.dev/gh/wangzan101/mika/content-transcribe

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencestranscript-output-formats.md

≈309 tokens on demand. Your agent reads this file only when SKILL.md points to it.

几种整理结果的写法

时间一律写成「分:秒」,超过一小时写「时:分:秒」。估出来的时间前面加「约」。

摘要

五到十句,第三人称、现在时,讲清这期内容的主题、主要论点和结论。不加评价。

章节目录

每行一个时间加一个短标题,标题不超过十五个字:

00:00 开场与话题
03:40 为什么会有这个问题
09:15 两种做法的对比
21:30 实际数据
35:05 听众提问

分章节摘要

章节标题后面括号写这一章大约多长,下面两三句写这一章实际讲了什么:

### 03:40 为什么会有这个问题(约 5 分钟)
主讲人回顾了这个问题的由来,举了两个常见的例子。

### 09:15 两种做法的对比(约 12 分钟)
比较了做法甲和做法乙的成本和效果,结论是……

引文

原话照录,后面写出现的时间;是字幕原文还是翻译,要注明:

「先把数据弄干净,比换模型更重要。」—— 12:18

改写成文章

  • 一个标题
  • 一段开头,说这是根据哪一期内容整理的
  • 每个主要话题一个小标题,下面成段叙述
  • 关键原话用引文格式,带时间
  • 结尾一段:要点或可以照着做的建议

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 0c258ac. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 4 days ago
display
把内容整理成文字
aliases
[
  "总结视频",
  "整理播客",
  "文章摘要",
  "提取字幕"
]
apps
[
  "bilibili",
  "xiaohongshu"
]
Other metadata
sites
[
  "youtube.com",
  "xiaoyuzhoufm.com"
]
terms
[
  "摘要",
  "总结",
  "转录",
  "字幕",
  "播客",
  "章节",
  "要点",
  "引文",
  "文字稿"
]

README badge

README badge for wangzan101/mika/content-transcribe