yt-chapters
Skill10 starsChanged 29 days agoMITView on GitHub
Draft YouTube chapters from a transcript and check them against YouTube's rules so they actually appear. Use for "add chapters", "timestamps", "split this video into sections".
6 other projects use a version of this.
Adopted by
Most recently taken up by
- uplika/uplika-plugintheir own version, first seen Oct 25, 2026
- swayamdhawan/youtube-agenttheir own version, first seen Oct 15, 2026
- ahmedsakri/youtube-agent-protheir own version, first seen Oct 15, 2026
- nessalazne/youtube-agent-skilltheir own version, first seen Sep 23, 2026
- Jakeschincariol/youtube-agent-skilltheir own version, first seen Sep 16, 2026
- tylerprogramming/claude-skillstheir own version, first seen Aug 9, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- Jakeschincariol/youtube-agent-skill★ 47same name
- nessalazne/youtube-agent-skill★ 5same name
- uplika/uplika-plugin★ 3same name
- ahmedsakri/youtube-agent-pro★ 1same name
- swayamdhawan/youtube-agent★ 0same name
- tylerprogramming/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- yt-auditSkill
- yt-commentSkill
- yt-editSkill
- yt-packageSkill
- yt-planSkill
- yt-researchSkill
- yt-retentionSkill
- yt-scriptSkill
- yt-seoSkill
- yt-shortsSkill
- yt-viralSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 28
Read ~/.claude/youtube/voice.md if it exists: chapter titles are the creator's words, not yours.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
yt-chapters
python3 ${CLAUDE_SKILL_DIR}/chapters.py transcript.srt --target 8The tools live in this skill's folder. ${CLAUDE_SKILL_DIR} is that folder in Claude Code; anywhere
it does not expand (claude.ai, Codex), use the folder this SKILL.md was loaded from.
It reads transcripts with ../yt-edit/deadair.py, so install the two together.
To fetch a video's own captions:
yt-dlp --skip-download --write-auto-subs --sub-langs en --sub-format vtt -o transcript "<video url>"Before you start
Read ~/.claude/youtube/voice.md if it exists: chapter titles are the creator's words, not yours.
Without it, title plainly and mention that the voice file would sharpen them.
YouTube's rules
A list that breaks any of these silently is not shown as chapters at all:
- the first timestamp is 00:00
- at least three chapters
- each at least ten seconds long
- in ascending order
The tool checks all four and says so when a list fails. Some channels must also enable advanced features in Studio before chapters appear; if a valid list does not show, check that first.
Retitle every line
chapters.py is good at boundaries - it scores the pauses taken and how much the vocabulary changes
across them. Its titles are just the topic words. Rewrite each as the promise of that section, in
three to five words, in the creator's voice.
A section you cannot name in five words is two sections, or filler. That is worth telling the creator too.
Before you hand it over
This skill drafts; you publish. End with the copy-ready block and one question: post it as is, or another pass?
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

