agentleFS
milad-ahmdmilad-ahmd/agent-skills/skills/youtube-seo-optimizer/SKILL.md

youtube-seo-optimizer

Skill5 starsChanged 17 days agoMITView on GitHub

Optimizes YouTube videos and channels for search and click-through, covering keyword research, titles, descriptions with chapters, tags, thumbnail concepts, end screens, playlists, channel page audits, and analytics reviews. Use when the user asks for YouTube titles, thumbnail ideas, tags, chapters, the video description box, better CTR or search ranking, or a YouTube channel audit.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start from the video topic and the viewer's intent: how-to, review, comparison, entertainment.

    line 12
  2. Distinctive:

    Never use clickbait the video doesn't deliver on, because that destroys retention.

    line 21
  3. Distinctive:

    Don't promise rankings or quote invented search volumes.

    line 57
  4. Distinctive:

    Never use misleading metadata or keyword stuffing, which violate YouTube's spam policies.

    line 58

≈ “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.

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

YouTube SEO Optimizer

Get more people to find the video (search and suggested) and click on it (CTR).

1. Keyword research

  • Start from the video topic and the viewer's intent: how-to, review, comparison, entertainment.
  • Mine real queries from YouTube autocomplete ("topic a…", "how to topic…"), the "People also search" box and the titles of top-ranking videos. Ask the user to paste these, or fetch them with a browser or search tool if one is available.
  • Choose one primary keyword plus 2–4 secondary ones. Prefer specific long-tail phrases for small channels.

2. Title (5 options)

  • 60 characters or fewer so nothing gets cut off, with the primary keyword near the start where it sounds natural.
  • Combine a keyword with a curiosity or benefit angle: numbers, a timeframe, a result, a contrast ("I Tried X for 30 Days (Honest Results)").
  • The title and thumbnail should complement each other, not repeat the same words.
  • Never use clickbait the video doesn't deliver on, because that destroys retention.

3. Thumbnail concepts (3 options)

For each: the main subject (a face with clear emotion, or the object), 3–4 words of text at most, a high-contrast color scheme and one focal point. It must be readable at mobile size. Describe the composition precisely enough for a designer or an image tool, and suggest an A/B test with YouTube's "Test & Compare" feature.

4. Description

Line 1–2: hook + primary keyword (shows in search)
Link/CTA (lead magnet, product) — above the fold
150–300 words: what viewers learn, naturally using secondary keywords
CHAPTERS:
0:00 Intro
0:45 ...
Resources / links mentioned · Related videos/playlist · Social links
#hashtag1 #hashtag2 #hashtag3 (max 3, shown above title)

Chapters must start at 0:00, list at least 3 timestamps, and each chapter must be at least 10 seconds long. Build them from the transcript if one is provided.

5. Tags, end screen, playlists

5–10 tags (tags matter little, but they help with misspellings), plus end-screen and card suggestions pointing to the best related video and playlist placement for binge sessions.

6. Channel audit

Banner value proposition, channel trailer, sections layout, about/keywords, upload consistency, playlist structure and content-gap ideas based on what's working for competitors.

7. Analytics review (from data the user provides)

Impressions, CTR (benchmark against the channel's own average), average view duration, the audience retention graph (look for dips and spikes), traffic sources, and returning vs new viewers. Diagnose: low CTR means the title or thumbnail needs work, and low retention means the hook or pacing does (pass it to youtube-script-writer). Then recommend the next 3 videos to make.

Rules

  • Don't promise rankings or quote invented search volumes. Label estimates clearly.
  • Never use misleading metadata or keyword stuffing, which violate YouTube's spam policies.

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.