Yt chapters skill
Write YouTube chapters from a transcript, validated against YouTube's own rules so they actually render.
by Jakeschincariol·MIT license·★ 1,136 Stars on the repo·GitHub ↗
npx degit Jakeschincariol/youtube-agent-skill/skills/yt-chapters#main ~/.claude/skills/yt-chaptersChecked ·commit main
Inside this skill
SKILL.md · the author's own words# yt-chapters ```bash python3 chapters.py transcript.srt --target 8 ``` ## The rules, which are not optional A chapter list that breaks any of these silently does not become chapters at all - the block just sits in the description doing nothing: - The first entry must be **00:00**. - There must be **at least three**. - Each must be **at least 10 seconds** long. The tool checks all three and tells you when a list is invalid rather than letting you paste it.
Word-for-word excerpt, not a result. Read the full SKILL.md ↓
Files of Yt chapters
Show the full text40 lines
yt-chapters
python3 chapters.py transcript.srt --target 8
The rules, which are not optional
A chapter list that breaks any of these silently does not become chapters at all - the block just sits in the description doing nothing:
- The first entry must be 00:00.
- There must be at least three.
- Each must be at least 10 seconds long.
The tool checks all three and tells you when a list is invalid rather than letting you paste it.
Retitle every line
chapters.py finds the BOUNDARIES well - it scores the pauses you actually took by how much the
vocabulary shifts across them. The titles it emits are the topic words, and they are a draft. A
chapter called "Thumbnails Titles Packaging" is a placeholder. Rewrite each one as the promise of
that section, in the user's voice, three to five words.
Chapters are also a retention diagnostic: if a section cannot be named in five words, it is two sections or it is filler.
The gate
Nothing here publishes. This skill writes and you publish. Every output ends in a block the user copies, and the last line of every run is the question: ship it, or change it?
| 1 | |
| 2 | name yt-chapters |
| 3 | description >- |
| 4 | Write YouTube chapters from a transcript, validated against YouTube's own |
| 5 | rules so they actually render. Use for "add chapters", "timestamps", |
| 6 | "break this video into sections". |
| 7 | |
| 8 | |
| 9 | # yt-chapters |
| 10 | |
| 11 | |
| 12 | python3 chapters.py transcript.srt --target 8 |
| 13 | |
| 14 | |
| 15 | ## The rules, which are not optional |
| 16 | |
| 17 | A chapter list that breaks any of these silently does not become chapters at all - the block just |
| 18 | sits in the description doing nothing: |
| 19 | |
| 20 | The first entry must be **00:00**. |
| 21 | There must be **at least three**. |
| 22 | Each must be **at least 10 seconds** long. |
| 23 | |
| 24 | The tool checks all three and tells you when a list is invalid rather than letting you paste it. |
| 25 | |
| 26 | ## Retitle every line |
| 27 | |
| 28 | `chapters.py` finds the BOUNDARIES well - it scores the pauses you actually took by how much the |
| 29 | vocabulary shifts across them. The titles it emits are the topic words, and they are a draft. A |
| 30 | chapter called "Thumbnails Titles Packaging" is a placeholder. Rewrite each one as the promise of |
| 31 | that section, in the user's voice, three to five words. |
| 32 | |
| 33 | Chapters are also a retention diagnostic: if a section cannot be named in five words, it is two |
| 34 | sections or it is filler. |
| 35 | |
| 36 | ## The gate |
| 37 | |
| 38 | Nothing here publishes. This skill writes and you publish. Every output ends in a block the user |
| 39 | copies, and the last line of every run is the question: **ship it, or change it?** |
| 40 |
Discussion
Browse more free Claude skills.