agentleFS
UXMagicaiUXMagicai/seosorted-skills/skills/youtube-channel-audit/SKILL.md

youtube-channel-audit

Skill0 starsChanged 41 days agoMITView on GitHub

Audit the YouTube SEO of any public channel or video with SEOsorted — channel stats, upload cadence, engagement, top videos, and a per-video metadata audit (title, description, tags, chapters, captions, keyword placement) with pass rates — or review the workspace's own connected channel. Use when the user asks to audit a YouTube channel, review video SEO or metadata, benchmark a competitor channel, or check why videos don't get found.

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

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:

    Add target_keyword for keyword checks in title, description opening and tags.

    line 11

≈ “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 channel audit

Any public channel or video

  1. analyze_any_youtube_channel with channel (URL, @handle or UC… id) and sample (5–50 recent uploads, default 30). Returns subscribers, median and average views, engagement, upload cadence, Shorts share, the five most-viewed videos, a per-video metadata audit and channel-wide pass rates. Free.
  2. Add target_keyword for keyword checks in title, description opening and tags.
  3. profile: true adds an AI read of content mix, tone and recurring topics — 1 keyword lookup; ask first.
  4. Individual videos: videos (up to 10 URLs or ids) instead of channel; with 5 or fewer, captions are read to check whether the keyword is spoken in the opening (transcripts: false skips that).
  5. Fuller stats: research_youtube operation: "channel_stats" with channel (free) — uploads in the last 30/90 days and recent videos.

Checks cover title length, description length, whether the first 150 characters restate the title, tag count, chapters on videos over 3 minutes.

The workspace's own channel

manage_my_youtube_channel operation: "analysis" (stored analysis) and "published" (videos with views, AI-answer citation counts and 30-day change). "run_analysis" refreshes it in the background (no metered credits). "update_video" only changes SEOsorted's records, never YouTube.

Output

Scorecard: stats, cadence, pass rate per check. Then the 5 highest-impact fixes with the videos they apply to, and for a competitor, what they do better.

Compare with find_youtube_videos_cited_by_ai to see which videos AI answers cite instead.

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.