ChapterKitv1.0.0

Checks YouTube's chapter rules (first at 0:00, at least three, each at least 10 seconds, in order) and snaps chapters to the sentence where each topic starts.

See what you can make

Made with this SkillChapters for YouTube, podcasts, web players and files

Six chapters, snapped to sentences

Open full example

What you get

Chapters for YouTube, podcasts, web players and files

What you can make

  • Checks YouTube's chapter rules (first at 0:00, at least three, each at least 10 seconds, in order) and snaps chapters to the sentence where each topic starts.
  • Writes the YouTube description block, Podcasting 2.0 JSON chapters, WebVTT chapters, a CSV and FFmpeg metadata.
  • Embeds chapter markers in MP4, M4A, MOV and MP3 without re-encoding, reads them back with ffprobe, and includes a studio beside the transcript.
Explore delivered files6 groups
  • youtube-description.txt
  • chapters.json (Podcasting 2.0)
  • chapters.vtt for HTML5 players
  • <file>-chapters.mp4 or .mp3 with markers embedded
  • index.html preview with a chapter timeline
  • Offline studio beside the transcript

Good fit

YouTubers, educators, podcasters and course creators publishing long videos and episodes.

Know the limits

Checks, snaps and writes chapters; it does not transcribe, choose topics without approval or upload. YouTube may still decide not to show chapters.

About this skill

Your agent reads the transcript in a condensed outline, proposes where each topic starts and a short title, and you approve them. ChapterKit snaps each chapter to the nearest sentence start, preferring one after a pause, and checks YouTube's rules: a first chapter at 0:00, at least three chapters, each at least ten seconds, in order and inside the video, with repeated or very long titles flagged. It writes the timestamps for the YouTube description, Podcasting 2.0 JSON chapters for podcast apps, WebVTT chapters for web players, a CSV and FFmpeg metadata, and with FFmpeg embeds chapter markers in MP4, M4A, MOV or MP3 without re-encoding, reading them back with ffprobe to confirm. A preview page shows the chapters on a timeline over the media, and a studio lets you edit chapters beside the transcript with the rules checked as you type. Requires Node.js 20+; FFmpeg to embed markers.

FROM PACKAGE TO FIRST RESULT

Your first result, with your agent

Choose a starting point, add the content you already have, then let your agent check the setup and create one result.

View example result

Purchase access is required. Unzip the package into the project folder below, or let your agent follow the installation guide. .agents/skills/chapterkit

Your project name, audience and the content or images you already have are enough to start. Your agent will ask for anything essential that is missing.

3. Let your agent guide the first result

Package location: .agents/skills/chapterkit

Use ChapterKit to add chapters to my 25-minute tutorial from its transcript. Start from examples/chair-restoration.json.

Use a new output folder and preserve existing files. Inspect the actual deliverables (youtube-description.txt, chapters.json (Podcasting 2.0), chapters.vtt for HTML5 players), open the visual result and explain failed checks. An incomplete dependency check is not a successful result. Ask before paid services and do not publish automatically.
Before calling it done
  • Dependencies checked before rendering
  • Actual files open and work with your content
  • Editable source saved in a new folder
Made your first result? Share your experience →
Installation options & technical requirements

Start with your agent

Give this request to Claude Code, Codex or Cursor. Your agent can collect the missing details and guide your first result.

Use ChapterKit to add chapters to my 25-minute tutorial from its transcript. Start from examples/chair-restoration.json.

Purchase access is required to install the package. Technical commands are available below when you need them.

US$4.99 · MIT licenseNode.js 20+ · FFmpeg to embed markers · no API keyNo API key or paid provider
  1. 01

    Choose your agent

    These steps use a project folder. Open the project in your agent and run terminal commands from its root.

    Codex directory guide

    Package folder .agents/skills/chapterkit

  2. 02

    Add the package

    Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.

    Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.

  3. 03

    Run the included sample

    Manual sample commands and technical details

    Read SKILL.md, review the generator and check its runtime requirements before running:

    cd .agents/skills/chapterkit
    No installation needed
    node scripts/render.mjs --input examples/chair-restoration.json --subs examples/chair-restoration.srt --output ./chapters
    Your first result

    Paste youtube-description.txt into the description, link chapters.json from the podcast feed, and publish the -chapters file.

    The tutorial and its transcript are fictional. ChapterKit checks and writes chapters; the agent proposes topics from the transcript and the user approves them.

    If chapters already exists, change the output to ./chapters-2. Existing files are never overwritten.

    Prefer to ask your agent?

    Use ChapterKit to add chapters. Read my transcript, propose chapter starts and titles for my approval, snap them to sentences, check YouTube's rules, and give me the description block, podcast chapters and a copy of my file with chapter markers.

Reviews

Share your first result

Tried this workflow? Help others decide with an honest review.

Before you choose this Skill

How do I get ChapterKit?

The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.

Which agents can use this skill?

This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.

What files can this workflow generate?

The documented 1.0.0 workflow lists: youtube-description.txt; chapters.json (Podcasting 2.0); chapters.vtt for HTML5 players; <file>-chapters.mp4 or .mp3 with markers embedded; index.html preview with a chapter timeline; Offline studio beside the transcript. Some files or exports are optional; follow the package’s setup and inspect the delivered result.

What should I check before using the result?

The tutorial and its transcript are fictional. ChapterKit checks and writes chapters; the agent proposes topics from the transcript and the user approves them.

$4.99One-time purchase