aiagentwithdhruvaiagentwithdhruv/skills/cross-niche-outliers/SKILL.md

cross-niche-outliers

Skill16 starsChanged 9 months agoMITView on GitHub

Find viral YouTube videos from adjacent business niches to extract content patterns and hooks. Use when user asks to find content inspiration, YouTube outliers, viral video patterns, or cross-niche content ideas.

Reads credentials

3 other projects use a version of this, 3 of them edited.

Adopted by

Most recently taken up by

MohamedEssam0-0/claude-skillsedited, first seen Oct 11, 2026
phuongdo/claude-skillsedited, first seen Feb 17, 2026
nickjwells/skills-workspaceedited, first seen Feb 1, 2026

Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 3
nickjwells/skills-workspace★ 2898% same
MohamedEssam0-0/claude-skills★ 098% same
phuongdo/claude-skills★ 098% same
Wrote their own version · 0
None found.
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 repository39 other files it gives its agents.
- add-webhookSkill
- aws-production-deploySkill
- build-in-public-youtubeSkill
- casualize-namesSkill
- classify-leadsSkill
- create-proposalSkill
- design-websiteSkill
- euron-qaSkill
- excalidraw-diagramSkill
- excalidraw-visualsSkill
- generate-reportSkill
- ghost-browserSkill
- gmail-inboxSkill
- gmail-labelSkill
- gmaps-leadsSkill
- image-to-videoSkill
- instantly-autoreplySkill
- instantly-campaignsSkill
- linkedin-carousel-handwrittenSkill
- literature-researchSkill
- local-serverSkill
- mac-controlSkill
- modal-deploySkill
- Nano Banana 2 Image Generation MasterSkill
- onboarding-kickoffSkill
- pan-3d-transitionSkill
- recreate-thumbnailsSkill
- scrape-leadsSkill
- send-telegramSkill
- skill-builderSkill
- skool-monitorSkill
- skool-ragSkill
- thumbnail-generatorSkill
- title-variantsSkill
- upwork-applySkill
- video-editSkill
- welcome-emailSkill
- whisper-voiceSkill
- youtube-outliersSkill

The file

We split this skill into the rules it gives an agent

3 rules. 3 are common, 0 are distinctive, and 0 are very specific to this project.

3
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
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

Common:
Search keywords (50 videos per keyword)
line 42
Common:
Run weekly for ~100 outliers
line 107
Common:
Use title variants as starting points
line 110

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Cross-Niche Outlier Detection

Goal

Identify high-performing videos from adjacent business niches to extract transferable content patterns, hooks, and structures. These outliers provide inspiration for content ideation without being directly competitive.

Two Approaches

1. TubeLab API (RECOMMENDED)

# Default: 1 query = 5 credits, ~100 outliers from last 30 days
python3 ./scripts/scrape_cross_niche_tubelab.py

# Custom search term
python3 ./scripts/scrape_cross_niche_tubelab.py --terms "business strategy"

# Skip transcripts (faster, cheaper)
python3 ./scripts/scrape_cross_niche_tubelab.py --skip_transcripts

Pros: Pre-calculated scores, no rate limiting, fast Cons: 5 credits per query

2. yt-dlp Scraping (LEGACY)

python3 ./scripts/scrape_cross_niche_outliers.py

Use only if TubeLab credits are exhausted. Often fails due to rate limiting.

Scripts

./scripts/scrape_cross_niche_tubelab.py - TubeLab API (recommended)
./scripts/scrape_cross_niche_outliers.py - yt-dlp direct scraping
./scripts/generate_title_variants.py - Generate title variants for outliers

Process

1. Video Discovery

Search keywords (50 videos per keyword)
Monitor business channels (15 videos per channel)
Deduplicate and filter noise

2. Outlier Scoring

Base score: video views / channel average views
Recency boost: <1 day = 2x, <3 days = 1.5x, <7 days = 1.2x
Threshold: 1.1x or higher (10% above average)

3. Cross-Niche Scoring

Modifiers applied to base score:

-20% per technical term (API, Python, code, SDK)
+30% for money hooks ($, revenue, income, profit)
+20% for time hooks (faster, productivity)
+20% for curiosity gaps (?, "this changed everything")
+10% for listicles (numbers in title)

4. Transcript & Summary

Fetches transcript (youtube-transcript-api, Apify fallback)
Claude summarizes: hook, structure, how to adapt
Raw transcript saved for deeper analysis

5. Title Variant Generation

For each outlier, generates 3 title variants adapted to your niche.

6. Output to Google Sheet (19 columns)

Cross-Niche Score, Outlier Score, Days Old, Category, Title, Video Link, Views, Duration, Channel, Thumbnail, Summary, Title Variants 1-3, Raw Transcript, Publish Date, Source

TubeLab Options

Flag	Description	Default
`--queries N`	Number of searches (5 credits each)	1
`--terms "a" "b"`	Custom search terms	entrepreneur
`--min_views N`	Minimum views	10,000
`--max_days N`	Max video age	30
`--skip_transcripts`	Skip transcripts	False

Keyword Tiers

Tier 1: Adjacent Business/Tech

"AI for business", "ChatGPT business use cases", "no-code automation"

Tier 2: Broad Business

"scale your business", "solopreneur success", "founder productivity"

Tier 3: Money/Revenue Hooks

"increase revenue", "passive income systems", "10x your income"

Monitored Channels

Alex Hormozi, My First Million, Starter Story, Colin and Samir, Ali Abdaal, Think Media, Iman Gadzhi, Pat Flynn, GaryVee, MrBeast, Justin Welsh, Charlie Morgan

Output

Google Sheet: "Cross-Niche Outliers v2 - [timestamp]"
~100 outliers with 19 columns
Sorted by publish date (most recent first)
3 title variants + raw transcript per outlier

Environment

TUBELAB_API_KEY=your_key
ANTHROPIC_API_KEY=your_key
APIFY_API_TOKEN=your_token (optional fallback)

Workflow

Run weekly for ~100 outliers
Review by Cross-Niche Score
Pick outlier with good thumbnail/title
Use title variants as starting points
Recreate thumbnail with your face (see recreate-thumbnails skill)

Schema

Inputs

Name	Type	Required	Description
`terms`	array	No	Custom search terms (default: 'entrepreneur')
`queries`	integer	No	Number of TubeLab searches (5 credits each, default: 1)
`min_views`	integer	No	Minimum views (default: 10,000)
`max_days`	integer	No	Max video age in days (default: 30)
`skip_transcripts`	boolean	No	Skip transcript fetching (faster)

Outputs

Name	Type	Description
`sheet_url`	string	Google Sheet with ~100 outliers (19 columns)

Credentials

Name	Source
`TUBELAB_API_KEY`	.env
`ANTHROPIC_API_KEY`	.env
`APIFY_API_TOKEN`	.env (optional fallback)

Composable With

Skills that chain well with this one: title-variants, recreate-thumbnails

Cost

5 TubeLab credits per query + Claude API

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.

Check your setup, free