niche-validator
Skill91 starsChanged 11 days agoMITView on GitHub
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.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ORBWEVA/founder-metricstheir own version, first seen Apr 27, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- ORBWEVA/founder-metrics★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-channel-riskSkill
- channel-analysisSkill
- comment-miningSkill
- competitor-researchSkill
- monetization-researchSkill
- niche-bendingSkill
- niche-finderSkill
- niche-watchlistSkill
- reverse-engineer-channelSkill
- script-breakdownSkill
- sponsorship-prospectingSkill
- thumbnail-conceptsSkill
- title-formulasSkill
- trend-reportSkill
- tubelab-mcpSkill
- video-ideationSkill
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
- Distinctive: line 95
If it runs long, cut whole items.
- Very specific: line 101
Do not search without publishedAtFrom and classificationQuality at "neutral" or above, or the results fill with low-effort videos.
- Distinctive: line 102
Do not present the scores as measurements.
- Distinctive: line 103
Do not call a niche open on big views alone.
- Distinctive: line 104
Do not count huge views with almost no likes as demand.
- Distinctive: line 105
Do not name a format from fewer than 3 outliers on different channels.
- Distinctive: line 106
Do not judge fewer than 10 on-topic channels.
≈ “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.
Files
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
- 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.
- 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.
- 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 🟢.
- 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.
- Score all three yourself for this exact niche or idea, from all you read. Say why wherever you differ from the formula.
- 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
# ⚖️ 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.jpgimage, on its own line under the heading, linked to the video.
Common Pitfalls
- Do not search without
publishedAtFromandclassificationQualityat"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.
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.

