channel-analysis — Claude Code skill for YouTube channel analysis
The channel-analysis Claude Code skill examines a YouTube channel’s positioning, strong points, and possible obstacles. It compares recent uploads with the channel’s median views and outlines experiments to try next.
MIT ★ 288 updated 2026-11-15
/plugin marketplace add TubeLabHQ/youtube-research-skills
/plugin install youtube-research@tubelabWhat channel-analysis does
The skill assesses a YouTube channel’s positioning and identifies changes to test first. It compares the median views with the latest 4–6 long-form uploads, checks their thumbnails, and searches for other material aimed at the same audience. Shorts are excluded.
The report highlights what is working and what may be holding the channel back, with video examples and view data to support its findings. It also suggests three tests and gives a pass criterion for each. TubeLab MCP is required.
Searches need publishedAtFrom and classificationQuality set to neutral or higher; otherwise, results can fill with low-effort videos. Low views alone do not count as a problem, and suspected causes are framed as evidence-based possibilities rather than facts.
What it helps with
- compare recent video views with the channel median
- spot formats and videos that perform better than others
- identify positioning issues and mismatches in title promises
- draft three tests for upcoming videos
Example prompts for the agent
- Analyze my YouTube channel’s positioning and suggest what to change first.
- Compare the channel’s latest long-form videos with its median views and identify what works.
- Find what may be holding this channel back and propose three video tests.
How to install channel-analysis
1Plugin marketplace
/plugin marketplace add TubeLabHQ/youtube-research-skills/plugin install youtube-research@tubelabThis installs the whole youtube-research plugin with all its skills
2Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill channel-analysis -a claude-code3Manually: put the files in place
~/.claude/skills/channel-analysis/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/channel-analysis/
1Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill channel-analysis -a codex2Manually: put the files in place
.agents/skills/channel-analysis/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill channel-analysis -a cursor2Manually: put the files in place
.cursor/skills/channel-analysis/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install TubeLabHQ/youtube-research-skills skills/channel-analysis2Manually: put the files in place
.github/skills/channel-analysis/SKILL.md1Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill channel-analysis -a gemini-cli2Platform CLI
gemini skills install https://github.com/TubeLabHQ/youtube-research-skills --path skills/channel-analysisManually: put the files in place
.devin/skills/channel-analysis/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about channel-analysis
How do I install channel-analysis in Claude Code?
Add the marketplace with /plugin marketplace add TubeLabHQ/youtube-research-skills, then install the skill with /plugin install youtube-research@tubelab.
What does channel-analysis do?
It compares recent long-form uploads with the channel’s median views, then reviews positioning and thumbnails. The report calls out strengths, potential obstacles, and three suggested tests.
What does channel-analysis need to run?
It requires TubeLab MCP. Searches also need publishedAtFrom and classificationQuality set to neutral or higher.
Source text
SKILL.md · MIT
---
name: channel-analysis
description: 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.
license: MIT
metadata:
author: tubelab
version: "5.0"
requires: tubelab-mcp
---
# 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
```markdown
# 📊 Channel Analysis: [{channel}]({url})
- **Diagnosis:** {one sentence, with numbers}
- **Positioning:** {who it serves and what it promises}
## ✅ What Works
### 1. {Finding}
[]({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.
© tubelab · MIT · TubeLabHQ/youtube-research-skills