Transcript to YouTube chapters: timestamps in the format the description needs
A prompt that turns a timestamped transcript into a chapter list for the YouTube description: first chapter at 0:00, at least three, each 10 seconds or more, titles that say what the viewer gets.
Turn the transcript below into YouTube chapters for the video description.
Format, one per line, nothing else:
M:SS Title
(H:MM:SS for videos over an hour; the first line must be 0:00)
Rules:
- The first chapter starts at 0:00; at least 3 chapters; no chapter shorter than 10 seconds. These are YouTube's stated requirements as of writing; treat them as parameters and check the current help page.
- A chapter starts where the topic changes, not every N minutes. Use the transcript's own words to find the boundary: 'next', 'now let's', a new question.
- Titles: 2-6 words, what the viewer gets ('Fixing the drift'), not what happens ('Section 3'). Sentence case. No emoji. Include the search term once if it fits naturally.
- Place each timestamp at the second where the new topic's first word starts, minus 1 second so the jump lands clean.
- Target {8-12} chapters for a {30}-minute video; fewer for shorter.
After the list, print it once more with each chapter's length in seconds and flag any under 10 s.
Transcript:
{paste transcript with timestamps} In Claude Code, paste the prompt as a message, or run /transcribe which does this end to end.
Steps
- Use the transcript of the final rendered file, not the raw footage: cuts move every timestamp.
- Paste the list into the description; chapters appear only when the format is exact and the first line is 0:00.
- Check the chapter markers in the player once; if one lands mid-sentence, move it back one second.
Tips
- Chapter titles are searched. A title that matches what people type ('export settings for Reels') does more than a clever one.
- The same list with timestamps removed is the outline for the pinned comment and the next video's description.
| works with | Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. · Claude: Paste into claude.ai or the Claude app. · ChatGPT: Paste into ChatGPT; works with any GPT model. · Any LLM: Model-agnostic: Gemini, Mistral, a local model. |
| skill | npx skills add fortunto2/solo-factory/transcribe · source |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | transcript-to-youtube-chapters-prompt.md |
Related
YouTube explainer, 8 minutes: the outline prompt with timestamps
A prompt that produces a timed outline for an 8-minute explainer: a cold open, a promise, five sections with a visual each, the mistake, a recap and one ask, before any script is written.
SRT cleanup: fix names from a glossary, merge short cues, cap line length
An agent prompt that takes a raw speech-to-text SRT and returns one you can publish: names fixed from your glossary, sub-second cues merged, lines wrapped at a character cap, timings untouched.
Generate a 10-clip b-roll pack for a talking-head video
One agent prompt that reads your transcript and writes ten generation prompts for cutaways that show what is being said, each tagged with the sentence it covers.
Upload, title, chapter and track videos on a YouTube channel (/youtube-channel)
Run a solo founder's YouTube channel from the terminal — upload through the YouTube Data API, subtitles as tracks, thumbnails, publish, bulk hide, link Shorts to the long video, and read the…
B-roll shot list from a transcript: the table to film or generate from
An agent prompt that reads a transcript and returns a shot table (timestamp, line, shot, source: have / film / generate) for a camera or a video model, grouped so each location is filmed once.
Burned subtitles for 9:16: position, lines, characters, colour, as parameters
Settings for subtitles burned into vertical video for muted feeds: above the platform UI, two lines, about 32 characters each, white with a dark outline. Starting values, checked on a phone.