agentleFS
nikhilbhansalinikhilbhansali/youtube-data-skills/skills/youtube-own-channel-analyzer/SKILL.md

youtube-own-channel-analyzer

Skill4 starsChanged 3 months agoMITView on GitHub

Comprehensive YouTube channel analysis using YouTube Data API v3. Analyze your own channel's performance metrics, content strategy, upload patterns, engagement rates, video performance, and growth trends. Use when users want to (1) Analyze their YouTube channel performance, (2) Get insights on video engagement and metrics, (3) Understand upload patterns and optimal posting times, (4) Identify top-performing content types, (5) Generate channel health reports, (6) Track subscriber and view growth patterns. Requires user's YouTube Data API v3 key.

  • Reads credentials

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run scripts/analyze_channel.py — resolve the path relative to this skill's own directory:

    line 32
  2. Very specific:

    Write to the path the script printed: reports/channel-analysis-<channel-slug>-<YYYY-MM-DD>.md

    line 48

≈ “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.

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

YouTube Own Channel Analyzer

Analyze your YouTube channel's performance using the YouTube Data API v3.

Usage

/youtube-own-channel-analyzer @MyChannel
/youtube-own-channel-analyzer https://youtube.com/@MyChannel
/youtube-own-channel-analyzer UCxxxxxxxxxxxxxxxxxxxxxx --max-videos 300

Instructions

Step 1: Parse Arguments

  • Channel (required): @handle, channel URL, or channel ID (UC...)
  • --max-videos N (optional): how many recent uploads to analyze (default: 200, 0 = all)

Step 2: Get the API Key

Get a key from Google Cloud Console with YouTube Data API v3 enabled. Check Claude memory first; if not found, ask the user to paste it.

Step 3: Run the Bundled Script

Run scripts/analyze_channel.py — resolve the path relative to this skill's own directory:

YT_API_KEY=API_KEY python3 <skill-dir>/scripts/analyze_channel.py "@CHANNEL" [--max-videos N]

Dependency: pip3 install google-api-python-client.

Step 4: Read the Data

reports/data/channel-analysis-<channel-slug>-<YYYY-MM-DD>.json

Step 5: Write the Report

Write to the path the script printed: reports/channel-analysis-<channel-slug>-<YYYY-MM-DD>.md

What the Script Computes

Channel Resolution

@handle → channels.list(forHandle=...); /channel/UC... and bare UC... → channels.list(id=...); legacy /user/name → forUsername. Never search.list.

Video Collection

contentDetails.relatedPlaylists.uploads → playlistItems.list pagination → videos.list in batches of 50.

Content Types

Categorized by title/description/tag patterns:

TypePattern
Tutorialtutorial, how to, guide, learn
Reviewreview, unbox, first look, comparison
Vlogvlog, day in, life, daily
Educationalexplain, education, lesson
Gaminggameplay, game, gaming, stream
Musicmusic, song, cover, lyrics
Otherno match

Duration Buckets

Short (<5 min), Medium (5-15 min), Long (15-30 min), Very Long (30+ min).

Performance Metrics vs Benchmarks

MetricFormulaBenchmark
View-to-sub ratioviews / subscribers10-20%
Engagement rate(likes + comments) / views1-5%
Like ratelikes / views3-7%
Comment ratecomments / views0.5-2%
Viral thresholdviews > 5x subscribersflagged per video
Underperformingviews < 10% of subscribersflagged per video

The benchmarks ship inside the JSON as benchmarks so the report can compare directly.

Upload Patterns

Day-of-week and hour-of-day distribution, average days between uploads, uploads per week, and a consistency score (population stddev of the gaps — lower is more consistent).

Title Analysis

Rates of numbers, emojis, questions, brackets, ALL-CAPS words, and "how to"; average title length in characters and words; the 20 most common non-stopword terms.

Output Report Structure

# Channel Analysis Report: [Channel Name]
*Analyzed [date] | [N] videos*

## Executive Summary
- Subscribers, total views, videos, avg engagement, upload consistency
- One-line health verdict

## Channel Overview
- Basic info, statistics table, description, keywords, country, created date

## Content Analysis
- Category breakdown table (count, %, avg views, avg engagement)
- Duration distribution table
- Title patterns

## Performance Metrics
| Metric | This Channel | Benchmark | Verdict |
|--------|-------------|-----------|---------|
Compare each metric in `performance` against `benchmarks`.

## Upload Patterns
- Optimal day/hour, uploads per week, consistency stddev
- Day and hour distribution

## Engagement Analysis
- Top 5 high-engagement videos (`top_by_engagement`)
- Bottom 5 needing improvement (`needs_improvement`)
- Viral and underperforming counts

## Recommendations
- Content optimization, upload frequency, title suggestions
- Each recommendation tied to a specific number from the data

## Quota Usage
| Operation | Calls | Units |
|-----------|-------|-------|
Use the `quota_used.breakdown` block from the JSON.

Step 6: Report Completion

Tell the user the report path, subscriber/view/video counts, the health verdict, the top recommendation, and the quota consumed.

Quota Estimate

No search.list at all — this skill only touches its own channel.

OperationCallsUnits
channels.list (resolve)11
playlistItems.list (200 uploads)44
videos.list (batches of 50)44
Total (200 videos)~9

Roughly 1 unit per 25 videos analyzed. The previously documented search.list(channelId=...) route cost 100 units per 50 videos (~400 units for the same 200 videos). Daily default allowance is 10,000 units, resetting at midnight Pacific Time.

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.