agentleFS
TubeLabHQTubeLabHQ/youtube-research-skills/skills/channel-analysis/SKILL.md

channel-analysis

Skill91 starsChanged 11 days agoMITView on GitHub

Use when the user wants to analyze a YouTube channel for its positioning, what works, what holds it back, and what to change first. Requires the TubeLab MCP.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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. Distinctive:

    Check what works now for the same audience.

    line 22
  2. Distinctive:

    If it runs long, cut whole items.

    line 55
  3. Very specific:

    Do not search without publishedAtFrom and classificationQuality at "neutral" or above, or the results fill with low-effort videos.

    line 61
  4. Distinctive:

    Do not call fewer views a problem by itself.

    line 62
  5. Distinctive:

    Do not read a ratio of 1.0 as typical.

    line 63
  6. Distinctive:

    Do not judge uploads that are still gathering views, and do not mix in Shorts.

    line 64
  7. Distinctive:

    Do not state a cause as fact.

    line 65

≈ “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

Channel Analysis

Overview

A channel's median views show what a typical video gets. Its last few uploads show how it is doing now. Comparing the two tells you whether the channel is healthy, growing or declining. A format that gets fewer views each time it returns is worn out: keep what makes it work, and change what the title promises. A hit the channel never followed up is its cheapest opportunity.

Workflow

  1. Clarify scope only if needed. Unless told otherwise, the goal is reach, or conversion if the channel sells something.
  2. Compare the last 4 to 6 long-form uploads with the median.
  3. Fetch and view the thumbnail of every video you feature. If one fails to load, say so.
  4. Check what works now for the same audience. Two or three searches are enough.

Output Format

# 📊 Channel Analysis: [{channel}]({url})

- **Diagnosis:** {one sentence, with numbers}
- **Positioning:** {who it serves and what it promises}

## ✅ What Works

### 1. {Finding}

[![]({thumbnail})]({video url})

- [{title}]({video url}) · {views, ratio, date}
- **Why:** {one sentence}

## ⚠️ What Holds It Back
1. **{Problem}**
   - [{title}]({video url}) · {views, ratio, date}
   - **Fix:** {one sentence}

## 🧪 Next 3 Tests
1. **{Title to test}**
   - **Based on:** [{channel}]({url}) · [{title}]({video url})
   - **Pass if:** {views by day 30}
  • Length: about 600 words. Three items per section.
  • Language: plain words and short, complete sentences. Nothing compressed.
  • Bullets: one fact each, under 25 words, except quotes and verbatim titles. No extra sections or bullets.
  • If it runs long, cut whole items. Never cut proof, and never squeeze sentences.
  • Links: link every video, channel, moment, brand and offer you cite, built from IDs, handles and links in the data. Never guess one.
  • Thumbnails: use the 320px mqdefault.jpg image, on its own line under the heading, linked to the video.

Common Pitfalls

  • Do not search without publishedAtFrom and classificationQuality at "neutral" or above, or the results fill with low-effort videos.
  • Do not call fewer views a problem by itself. A healthy channel is a valid result.
  • Do not read a ratio of 1.0 as typical. Big hits pull the channel's mean up, so a median video sits below 1.0.
  • Do not judge uploads that are still gathering views, and do not mix in Shorts.
  • Do not state a cause as fact. Say what the evidence suggests.

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.