agentleFS
postoncehqpostoncehq/youtube-mcp/skills/youtube-tag-generator/SKILL.md

youtube-tag-generator

Skill1 starsChanged 47 days agoMITView on GitHub

Generate YouTube tags within the 500-character limit, delivered as hashtags for the description (which PostOnce sends as the video's tags) plus a full tag list to paste into YouTube Studio. Use when the user asks for a YouTube tag generator, YouTube tags, keywords for a video, or hashtags for a YouTube video or Short.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never use more than 15 hashtags on a video.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

YouTube tag generator

Build one tag set for one video. Tags are a small signal on YouTube: they mostly help with misspellings and closely related searches. The title, description and thumbnail matter more, so keep tags accurate and short rather than long and hopeful.

How tags reach YouTube through PostOnce

The MCP has no separate tags field. PostOnce takes up to 8 hashtags from the video's description and sends them as its tags (plus a generic video tag). So this skill delivers two things:

  1. Hashtags to include in the description: 3–8 single-word hashtags. These become the uploaded tags.
  2. A full tag list the user can paste into the Tags box in YouTube Studio (Details > Show more > Tags) after upload, for multi-word tags and anything beyond 8.

Before writing

Get or infer: the title, the main search keyword, what the video covers, the audience, and the channel or brand name. Read the description or transcript if there is one.

Building the full list

Order matters; put the most important tags first.

  1. The exact main keyword ("repurpose video content").
  2. 2–4 close variations and longer phrases people search ("how to repurpose videos", "repurpose youtube videos to tiktok").
  3. 2–4 broader topic tags ("content repurposing", "video marketing").
  4. Common misspellings or alternate names, only if real.
  5. The channel or brand name.

Budget: YouTube allows 500 characters for all tags combined. Commas count, and a tag with spaces counts its surrounding quotes, so count the list as YouTube will. Stop well before 500; 10–20 relevant tags is plenty.

Hashtags for the description

  • Letters, numbers and underscores only: #contentrepurposing, not #content-repurposing or #content repurposing. Anything after a hyphen or space is dropped.
  • YouTube shows the first three hashtags above the title, so put the best three first.
  • Never use more than 15 hashtags on a video; YouTube then ignores all of them. For Shorts, #shorts is optional; YouTube classifies Shorts from the video itself.

Anti-patterns

Tags for other creators' names or unrelated trending topics (YouTube treats misleading metadata as spam), repeating the same word in 20 forms, and single generic tags like "video" or "funny".

Output

Return:

  • Hashtags to include: one line, 3–8 hashtags, best three first.
  • YouTube Studio tags: one comma-separated line, then its character count against 500.

Offer to add the hashtags to the end of the description and publish or schedule with the postonce skill (confirm the channel, privacy and time before create_post). The full tag list is for the user to paste into YouTube Studio; the MCP can't edit a video after upload.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.