niche-watchlist — Claude Code skill for YouTube monitoring
The niche-watchlist Claude Code skill tracks YouTube niches and reports changes. It runs on a schedule to find new channels and channels whose median views have risen.
MIT ★ 288 updated 2026-11-15
/plugin marketplace add TubeLabHQ/youtube-research-skills
/plugin install youtube-research@tubelabWhat niche-watchlist does
The skill compares saved niche searches with the previous run and builds a digest of newly found channels and channels with higher median views. For each result, it examines popular videos, recurring topics, and title patterns, then fetches the thumbnail of the channel’s best video.
Search settings go in watchlist/config.json; stored channel metrics go in watchlist/state.json. Each run writes watchlist/<date>.md and refreshes the stored values. A channel counts as new based on its first-seen date, while a mover has median views more than 50% above its stored value. If state.json is missing, the first run establishes a baseline.
TubeLab MCP is required. Saved searches need publishedAtFrom, or older channels can crowd out newer results. The skill does not label a channel a breakout below 1K median views or with fewer than 5 videos.
What it helps with
- track newly found channels across saved YouTube niches
- spot channels whose median views have increased
- compare search results with the previous run
- compile a digest of channel topics and title patterns
Example prompts for the agent
- Track my saved YouTube niches and report what changed since the last run.
- Add a watchlist for budget travel channels and create the initial report.
- Review new and growing channels across my saved searches.
How to install niche-watchlist
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-watchlist -a claude-code3Manually: put the files in place
~/.claude/skills/niche-watchlist/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/niche-watchlist/
1Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill niche-watchlist -a codex2Manually: put the files in place
.agents/skills/niche-watchlist/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill niche-watchlist -a cursor2Manually: put the files in place
.cursor/skills/niche-watchlist/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install TubeLabHQ/youtube-research-skills skills/niche-watchlist2Manually: put the files in place
.github/skills/niche-watchlist/SKILL.md1Skills CLI (Vercel)
npx skills add TubeLabHQ/youtube-research-skills --skill niche-watchlist -a gemini-cli2Platform CLI
gemini skills install https://github.com/TubeLabHQ/youtube-research-skills --path skills/niche-watchlistManually: put the files in place
.devin/skills/niche-watchlist/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-watchlist
How do I install niche-watchlist in Claude Code?
Run these commands in order: /plugin marketplace add TubeLabHQ/youtube-research-skills, then /plugin install youtube-research@tubelab.
What does niche-watchlist do?
It compares saved YouTube niche searches across runs and creates a digest of new channels and channels with rising median views. It also examines recurring video topics and title patterns.
What does niche-watchlist need to run?
It requires TubeLab MCP. Saved searches also need the publishedAtFrom field.
Source text
SKILL.md · MIT
---
name: niche-watchlist
description: Use when the user wants to monitor YouTube niches on a schedule and get a digest of new or breakout channels. Requires the TubeLab MCP.
license: MIT
metadata:
author: tubelab
version: "5.0"
requires: tubelab-mcp
---
# Niche Watchlist
## Overview
Watch niches on a schedule and report only what changed since the last run. The two files below keep a fixed shape, so each run can be compared with the last one. For each new channel or mover, say what is worth learning from it.
## Workflow
1. Read `watchlist/config.json`. If it is missing, ask for 1 to 5 niches and write it.
2. Read `watchlist/state.json`. If it is missing, this run is a baseline, not a wave of breakouts.
3. Run each saved search once, exactly as saved. Compare only the channels it returns.
4. A new channel is one first seen since the last run. A mover is a known channel whose median views rose more than 50 percent over the stored value.
5. Read each new channel and mover, which is free. Look at its top videos by ratio, the topics it repeats and the title shapes it repeats. Fetch and view its best video's thumbnail, and say so if one fails to load.
6. Write `watchlist/<date>.md` on every run, then refresh the stored values.
`watchlist/config.json` (the saved search can hold other settings, such as a language):
```json
{ "niches": [ { "name": "budget travel", "search": { "query": ["budget travel tips"], "language": ["en"],
"publishedAtFrom": "month", "sortBy": "foundAt", "sortOrder": "desc", "size": 20 } } ] }
```
`watchlist/state.json`:
```json
{ "lastRun": "<date>", "niches": { "budget travel": { "<channelId>":
{ "handle": "@name", "subscribers": 0, "medianViews": 0, "firstSeen": "<date>" } } } }
```
## Output Format
```markdown
# 📡 Watchlist Digest: {date}
- **Since {last run}:** {n new and n movers, or "No change", or "Baseline"}
## {Niche}
### [{channel}]({url}) · {new or mover} · {subscribers} subs · {median} median views
[]({video url})
- **Worth studying:** ✅ {yes, and why in one sentence}
- **Topics working:** {two or three topics}
- **Title formulas:** {template}, for example [{title}]({video url})
- **Best recent video:** [{title}]({video url}) · {views, ratio, date}
- [{channel}]({url}) · {new or mover} · ❌ not worth studying: {why in one sentence}
```
- Length: about 600 words. Up to five channels per niche, strongest first. One line for a niche with no change, and one line for a channel not worth studying.
- 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 channels, not the summary line or proof.
- 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 save a search without `publishedAtFrom`, or old channels crowd out the new ones.
- Do not change a saved search between runs, or the differences are noise. An edited niche starts a new baseline.
- Do not call a channel new because it dropped out of the sample and came back. Check its first-seen date.
- Do not call a channel a breakout below 1K median views or 5 videos.
© tubelab · MIT · TubeLabHQ/youtube-research-skills