youtube-description-generator
Skill1 starsChanged 47 days agoMITView on GitHub
Write YouTube video descriptions with the keyword in the first two lines, chapters (timestamps) from a transcript, links and hashtags, within 5,000 characters, ready to publish with the PostOnce YouTube MCP. Use when the user asks for a YouTube description generator, a video description, YouTube chapters or timestamps, or to turn a transcript or script into a description.
In this repository8 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Write one description for one video, then hand it to the postonce skill as platform_options.description if the user wants to publish or …
- Very specific: line 32
Use 1:02:30 style for videos over an hour.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
YouTube description generator
Write one description for one video, then hand it to the postonce skill as platform_options.description if the user wants to publish or schedule.
Before writing
Get or infer: the video's title and search keyword, what it covers, the audience, the links to include (product, resources, socials, a related video), and a transcript with timestamps if the user wants chapters. Never invent links, sponsors, results or timestamps.
Structure
- First two lines (about 150 characters). They show in search and above "...more". State what the viewer gets and use the keyword naturally in the first sentence. No "In this video I will...".
- Summary. 2–4 short paragraphs in plain language. Work in related terms people search, once each. No keyword stuffing.
- Links. One per line with a label: "Free template: https://…". Put the most important link near the top if the video's goal is a click. Use clean URLs without
&query strings: PostOnce turns&into "and", which breaks the link. - Chapters. See below.
- Hashtags. 3–5 at the very end. See below.
Hard limit: 5,000 characters. Longer text gets cut off or rejected, so count before you hand it over.
Chapters from a transcript
- Build chapters only from real timestamps in the transcript or from the user. If the transcript has no timestamps, ask for them or skip chapters.
- The first chapter must be
00:00. Use at least three chapters, each at least 10 seconds long, in ascending order. YouTube ignores the list otherwise. - Format:
00:00 Intro,02:15 Setting up the account, one per line. Labels are short and specific; use the keyword in one or two where it fits. - Use
1:02:30style for videos over an hour.
Hashtags and tags
- YouTube shows the first three hashtags above the title. Put the most relevant three first.
- PostOnce sends up to 8 hashtags from the description as the video's tags, so choose them on purpose. Use letters, numbers and underscores only (
#videoediting, not#video-editing); anything after a hyphen or space is dropped. - YouTube ignores every hashtag on a video that has more than 15. Stay at 3–5 here; use the
youtube-tag-generatorskill for a fuller tag set.
Anti-patterns
Walls of text, a pasted transcript, repeated keywords, unrelated trending hashtags, links with no label, and &, < or > (PostOnce replaces them because YouTube rejects them).
Output
Return the description exactly as it will appear, then a line with its character count. Offer to publish or schedule with the postonce skill: pass it as platform_options.description and the title as platform_options.title on the YouTube target. Without description, YouTube gets the whole post content, so set both. Confirm the channel, privacy and time before calling create_post.
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.

