youtube-outliers
Skill0 starsChanged 41 days agoMITView on GitHub
Find outlier YouTube videos — videos with views several times their channel's median — for a topic or within one channel, plus the trending chart for a country, and read what made them work from their details, comments and transcript. Use when the user asks for outlier videos, viral video ideas, what's working on YouTube in their niche, breakout formats, trending videos, or a competitor channel's best videos.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- MohamedEssam0-0/claude-skillstheir own version, first seen Oct 11, 2026
- aiagentwithdhruv/skillstheir own version, first seen Mar 2, 2026
- phuongdo/claude-skillstheir own version, first seen Feb 17, 2026
- nickjwells/skills-workspacetheir own version, first seen Feb 1, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- nickjwells/skills-workspace★ 28same name
- aiagentwithdhruv/skills★ 16same name
- MohamedEssam0-0/claude-skills★ 0same name
- phuongdo/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository36 other files it gives its agents.
- ai-citation-outreachSkill
- ai-crawler-analyticsSkill
- ai-visibility-trackerSkill
- backlink-outreachSkill
- backlinksSkill
- brand-voice-setupSkill
- bulk-content-runSkill
- cannibalization-checkSkill
- comparison-pagesSkill
- competitor-analysisSkill
- content-calendarSkill
- content-refreshSkill
- domain-authority-checkSkill
- find-questionsSkill
- keyword-researchSkill
- link-building-playbooksSkill
- link-reclamationSkill
- llms-txt-generatorSkill
- page-seo-auditSkill
- publish-to-cmsSkill
- seo-auditSkill
- seo-master-planSkill
- seo-reportSkill
- seosortedSkill
- serp-analysisSkill
- site-settingsSkill
- statistics-pageSkill
- technical-audit-reportSkill
- technical-seo-checkSkill
- topic-clustersSkill
- update-and-republishSkill
- write-articleSkill
- youtube-channel-auditSkill
- youtube-citation-strategySkill
- youtube-creator-outreachSkill
- youtube-keyword-researchSkill
The file
Files
YouTube outliers
An outlier beat its own channel's normal by a wide margin, so the topic, title or format did the work, not the audience size. Those are the ideas worth copying.
Steps
- Outliers for a topic:
research_youtubeoperation: "outliers"withquery,multiplier(default 3; 5–10 for stricter) andlimit(up to 50). 1 keyword lookup credit. - Outliers within a channel: same operation with
channel(URL, @handle or UC… id) instead ofquery. Free. - Trending:
operation: "trending"withcountryand optionalcategory_id(e.g. 26 Howto & Style, 27 Education, 28 Science & Technology). Free. - Why it worked: for the top 3–5,
operation: "video_details"withvideo,comments: 10–20andtranscript: true(free). Note the title pattern, thumbnail promise, hook in the first 30 seconds, length, and what commenters ask for.
Free operations are capped at 300 YouTube lookups per workspace per hour.
Output
A table: video, channel, views, multiple of channel median, age, length, title pattern. Then 3–5 patterns that repeat, and video ideas for the user's channel that apply them to their own expertise — not copies.
Next
Turn ideas into topics and scripts with plan_youtube_videos (see youtube-citation-strategy); size their search demand with youtube-keyword-research.
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.