niche-validator — Claude Code skill: assess a YouTube niche
The niche-validator Claude Code skill evaluates whether a YouTube niche is worth entering. It compares market size, saturation, and revenue potential across sampled channels.
MIT ★ 288 updated 2026-11-15
/plugin marketplace add TubeLabHQ/youtube-research-skills
/plugin install youtube-research@tubelabWhat niche-validator does
The skill samples YouTube channels and rates a niche on market size, saturation, and revenue potential. It presents formula-based scores alongside a separate judgment, then gives one of three verdicts: enter, take a distinct angle, or stay out.
For a shortlist, it compares the options before examining the strongest one in depth. It looks for newer channels gaining traction, identifies formats used by successful creators, and finds topics they leave uncovered. The report also includes content ideas and draft video titles. TubeLab MCP is required to run the analysis.
What it helps with
- decide whether to enter a YouTube niche
- compare a shortlist of niches across three measures
- check whether newer channels are gaining ground
- spot successful formats and topics leaders leave uncovered
Example prompts for the agent
- Assess whether a channel about bicycle repair could work.
- Compare gardening, houseplants, and vegetable-growing niches.
- Check how saturated the budget smartphone review niche is.
How to install niche-validator
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 niche-validator -a claude-code3Manually: put the files in place
~/.claude/skills/niche-validator/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/niche-validator/
1Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill niche-validator -a codex2Manually: put the files in place
.agents/skills/niche-validator/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill niche-validator -a cursor2Manually: put the files in place
.cursor/skills/niche-validator/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install TubeLabHQ/youtube-research-skills skills/niche-validator2Manually: put the files in place
.github/skills/niche-validator/SKILL.md1Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill niche-validator -a gemini-cli2Platform CLI
gemini skills install https://github.com/TubeLabHQ/youtube-research-skills --path skills/niche-validatorManually: put the files in place
.devin/skills/niche-validator/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 niche-validator
How do I install niche-validator 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 niche-validator do?
It evaluates YouTube niches by market size, saturation, and revenue potential, then gives an entry verdict. It also looks for emerging channels, successful formats, and gaps in leaders’ coverage.
What does niche-validator need to run?
It requires TubeLab MCP.
Source text
SKILL.md · MIT
---
name: niche-validator
description: Use when the user wants to know whether a YouTube niche, or a shortlist of niches, is worth entering or already saturated. Requires the TubeLab MCP.
license: MIT
metadata:
author: tubelab
version: "5.0"
requires: tubelab-mcp
---
# Niche Validator
## Overview
One niche, one verdict: enter, enter with a twist, or stay out. A shortlist of up to three is compared first. The formula scores match TubeLab's Niche Analyzer. Your own scores set the verdict. The real test is whether new channels are breaking in.
## Workflow
1. Clarify scope only if needed. Name the niche in 2 to 3 words; for a channel, take it from its titles. Sample and score each shortlist niche the same way. For a new idea, do the same for the two existing niches it draws on, such as its topic and its format, and name both. Start with the last 3 months; widen to 6 months, then a year, if results are thin.
2. Search videos for the niche from two angles, sorted by views with no ratio floor. Take the first 10 to 15 on-topic channels behind the top results, where most recent titles serve the niche's audience. Skip channels under 1,000 subscribers. Read each for its most-viewed video as returned, average views and subscribers. Add a known leader only if the searches missed it.
3. Compute three scores from the sample. Leave out, and name, any channel whose views per subscriber exceed three times the sample's median. Do not leave a channel out because it is big. If a read and a search hit disagree, trust the read. Round each score, cap it at 100, then band it.
- Market Size: average each channel's most-viewed video, divide by 1,000,000, and multiply by 100.
- Unsaturated: for each channel, divide average views by subscribers. Average those ratios, divide by 1.1, and multiply by 100.
- Profitable: average the low RPM estimates from the search hits' channel data, divide by 7 dollars, and multiply by 100.
- Bands: under 50 is weak 🔴, 50 to 70 is fair 🟡, and 71 or more is strong 🟢.
4. For Breaking In, search once for young channels (joined in the last year, above 1K median views) in the niche with the best formula scores. View the thumbnail of every video you feature, and say if one fails.
5. Score all three yourself for this exact niche or idea, from all you read. Say why wherever you differ from the formula.
6. Name the formats behind the winners, by ratio on the same hits, what the leaders never cover, and two or three ideas that bend it.
## Output Format
```markdown
# ⚖️ Niche Verdict: {niche, or the strongest of the shortlist}
- **Verdict:** {enter, enter with a twist, or stay out}, {why, with numbers}
- **Sample:** {n} on-topic channels, {n} videos, {window, and whether it was widened}, {for a new idea: the two related niches sampled, by name}
- **Left out of the scores:** {channels, and why; drop this bullet if none}
## 🆚 Shortlist
{Only with a shortlist. Write "not scored" for a niche with fewer than 10 on-topic channels. Everything after this section is about the strongest niche.}
Each score here is my read of that niche. The formula scores for the strongest are below.
| Niche | Market Size | Unsaturated | Profitable | Verdict |
|---|---|---|---|---|
| {niche} | {my read} {band emoji} | {my read} {band emoji} | {my read} {band emoji} | {verdict} |
- **Why {niche}:** {one sentence on why it is the strongest}
## 📊 Scores
Formula scores come from the sample, computed like TubeLab's Niche Analyzer. My read is my own judgment of this exact {niche or idea}, from everything I read. Both run from 0 to 100.
{For a new idea, give one Formula column per related niche, headed by that niche's name. When My read differs from the formula, say why in a few words in Based on, such as "one video sets the average", "the idea is narrower than the niches sampled" or "the leaders are all old".}
| Score | Formula | My read | Based on |
|---|---|---|---|
| Market Size | {n} {🟢, 🟡 or 🔴} | {n} {band emoji} | viral views potential {n}, average views {n}, {"set by one video" if the band changes without it}, {why my read differs, if it does} |
| Unsaturated | {n} {band emoji} | {n} {band emoji} | reach beyond subscribers {ratio}, {why my read differs, if it does} |
| Profitable | {n} {band emoji} | {n} {band emoji} | RPM {band}, from {n} channels, {why my read differs, if it does}; if RPM is missing, say the score could not be computed |
Revenue estimate, unreliable outside English-speaking audiences:
| Views | 1K | 10K | 100K | 1M |
|---|---|---|---|---|
| Revenue | {band} | {band} | {band} | {band} |
## 🚀 Breaking In
- [{channel}]({url}) · {age, subscribers, median views}
## ✅ Formats That Work
### 1. {Format}
[]({video url})
- [{channel}]({url}) · [{title}]({video url}) · {views, ratio, date}
- [{channel}]({url}) · [{title}]({video url}) · {views, ratio, date}
- [{channel}]({url}) · [{title}]({video url}) · {views, ratio, date}
## 🎯 Gaps and Ideas
- **Leaders never cover:** {one sentence}
- **{Idea}:** {one sentence}
## 🌍 Other Languages
{Check French, German and Spanish markets only if the user asked or the niche looks saturated, since each costs more searches: market, channels found, open or not. Otherwise leave this section out.}
## 🧭 Entry Plan
- **Angle:** {the gap and the format, in one sentence}
- **First titles:** {three titles}
```
- Length: about 700 words, plus any shortlist. 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 present the scores as measurements. The formula estimates from a sample; yours are judgments.
- Do not call a niche open on big views alone. Ten established channels and no newcomer means it is closed.
- Do not count huge views with almost no likes as demand; they are usually paid.
- Do not name a format from fewer than 3 outliers on different channels.
- Do not judge fewer than 10 on-topic channels. Say what would settle it.
© tubelab · MIT · TubeLabHQ/youtube-research-skills