youtube-trending-scanner
Skill4 starsChanged 3 months agoMITView on GitHub
Scan what's trending right now in any YouTube niche using YouTube Data API v3. Find velocity outliers, rising channels, breakout videos, and emerging topics. Use when users want to (1) See what's trending in their niche right now, (2) Find breakout videos getting disproportionate views, (3) Discover rising channels with unusual traction, (4) Catch trends before they peak, (5) Find outdated content to remake, (6) Identify first-mover opportunities. Requires user's YouTube Data API v3 key.
- Reads credentials
In this repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- youtube-channel-breakdownSkill
- youtube-channel-insightsSkill
- youtube-comment-minerSkill
- youtube-competitor-analyzerSkill
- youtube-content-strategistSkill
- youtube-metadata-updaterSkill
- youtube-own-channel-analyzerSkill
- youtube-thumbnail-analyzerSkill
- youtube-thumbnailsSkill
- youtube-title-tag-optimizerSkill
- youtube-topic-researcherSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 27
Check Claude memory for a YouTube Data API v3 key.
- Very specific: line 32
Run scripts/scan_trending.py — resolve the path relative to this skill's own directory:
- Distinctive: line 52
Write to the path the script printed:
≈ “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.
Files
YouTube Trending Scanner
Scan what's trending right now in any YouTube niche -- find breakout videos, rising channels, and emerging topics.
Usage
/youtube-trending-scanner "meditation"
/youtube-trending-scanner "AI tools" --days 14
/youtube-trending-scanner "home cooking" --days 30Instructions
Step 1: Parse Arguments
- Niche/keyword (required): the niche to scan
- --days N (optional): time window to scan (default: 14, max: 30)
Step 2: Get the API Key
Check Claude memory for a YouTube Data API v3 key. If not found, ask:
"I need a YouTube Data API v3 key. You can get one from the Google Cloud Console. Please paste your key."
Step 3: Run the Bundled Script
Run scripts/scan_trending.py — resolve the path relative to this skill's own directory:
YT_API_KEY=API_KEY python3 <skill-dir>/scripts/scan_trending.py "NICHE" [--days N]Dependency: pip3 install google-api-python-client.
The script searches the window three ways (relevance, viewCount, date), pulls a 90-day baseline for comparison, then computes velocity outliers, rising channels, trending words/bigrams, format distribution, and publishing-rate change.
Step 4: Read the Data
reports/data/trending-scan-<niche-slug>-<YYYY-MM-DD>.jsonStep 5: Write the Report
Write to the path the script printed:
reports/trending-scan-<niche-slug>-<YYYY-MM-DD>.md# Trending Scanner: [Niche]
*Scanned [date] | Last [N] days | [N] videos analyzed*
## Hot Right Now
Overall trend assessment: Is this niche heating up, stable, or cooling down?
Compare recent publishing rate vs baseline.
## Breakout Videos (Velocity Outliers)
| # | Title | Views | Velocity (views/day) | Channel | Channel Size | Age |
|---|-------|-------|---------------------|---------|--------------|-----|
These videos are getting disproportionate views. What do they have in common?
## Trending Topics
Words and phrases appearing frequently in recent high-performing content.
Topic clusters and emerging themes.
## Rising Channels
Small channels getting unusual traction right now.
| Channel | Subs | Recent Videos | Recent Views | Avg View/Sub Ratio |
|---------|------|---------------|--------------|-------------------|
## Format Trends
What formats are being used? Which are performing best?
Shorts vs long-form breakdown.
## Content Velocity
- Current niche publishing rate vs baseline
- Is competition increasing or decreasing?
- Saturation signals
## Timely Content Recommendations
3-5 specific video ideas based on current trends:
- What to make THIS WEEK
- Why (data backing)
- Format and angle recommendation
## Trend Assessment
- Growing / Stable / Declining
- First-mover opportunities
- Risks and considerations
## Quota Usage
| Operation | Calls | Units |
|-----------|-------|-------|
Use the `quota_used.breakdown` block from the JSON.Step 6: Report Completion
Tell the user the report path, the trend assessment, the top breakout video, the number of rising channels found, and the quota consumed.
Quota Estimate
Trend detection depends on time-windowed keyword search, so search.list stays.
| Operation | Calls | Units |
search.list (relevance, viewCount, date, 90-day baseline) | 4 | 400 |
videos.list (batches of 50) | ~4 | ~4 |
channels.list (batches of 50) | ~3 | ~3 |
| Total | ~407 |
Daily default allowance is 10,000 units, resetting at midnight Pacific Time.
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.

