Discover YouTube Niche & Performance Intelligence · সর্বজনীন Open Skill
Discover YouTube Niche & Performance Intelligence
Find what works on YouTube — and investigate why. YouTube Opportunity Radar researches niches, micro-niches, competitors, channels, videos, and language × markets using public evidence. It can map a broad category down to its smallest useful micro-niches, compare demand and competition, identify outlier videos, and analyze the recurring patterns shared by high-performing content. Instead of only showing what is popular, it compares stronger-performing videos with normal content when evidence allows — helping reveal which hooks, topics, story structures, formats, characters, visual approaches, titles, thumbnails, and content patterns are associated with stronger performance. Explore the market from Category → Niche → Micro-Niche → Channel → Video → Content DNA, then continue deeper through four evidence-based research paths after every analysis. What would you like to investigate on YouTube? I can research a broad category, discover micro-niches, analyze a channel or video, compare competitors and markets, or map the recurring patterns behind high-performing content. You can start with something simple like: “Find promising animal micro-niches.” “Analyze this YouTube channel and its competitors.” “Why are these videos outperforming the channel's normal videos?” “Compare this niche across English, Spanish, Portuguese, Korean, and Turkish markets.”
Other
19 5 15
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/223892/2026-09-29/6htpteja.png
# YouTube Opportunity Radar
## When to use
- User wants to discover promising YouTube niches / sub-niches / micro-niches.
- User wants to analyze or validate a specific niche ("analyze senior health videos").
- User wants competitor intelligence on a channel or its competitors.
- User wants video/format intelligence on a successful video and the niche behind it.
- User wants cross-language / cross-market opportunity analysis.
- User wants to advance one step of an ongoing research project (deepen a niche, compare markets, generate video opportunities, etc.).
## Capability model (read first — honest limits)
This skill runs on real, currently-available tools. It does NOT have a YouTube API, private YouTube Studio/Analytics, Google Trends, or a search-volume database. Therefore:
- PRIMARY RESEARCH ENGINE = `search_web` (Tavily web search). Use it to discover videos, channels, niche discussions, rankings, articles, and community signals in the target language/market.
- VIDEO METADATA = `download_video` (YouTube/TikTok/IG, returns title/duration/file size + a temporary download link) and `fetch_video_info` (metadata-only, more platforms).
- VIDEO CONTENT = `download_video` → `recognize_video` (visuals/plot/style/format) and `transcribe_audio` (speech/dialogue/subtitles). Pass the returned `downloadUrl` verbatim (it may be a `shorturl://…` reference).
- THUMBNAILS = `recognize_image` on a public thumbnail URL found via search.
- REPORTS = `create_document` / `update_document` / `get_document`.
NEVER fabricate: search volume, RPM/CPM, private analytics, audience demographics, revenue, market size, trend statistics, channel metrics (subscribers/median views/upload frequency), API-derived metrics, future views, or viral probability. If a metric isn't actually retrievable, mark it INSUFFICIENT DATA or ANALYTICAL INFERENCE — never present it as measured fact.
## Reference files (read on demand, don't read all at once)
- `references/research-method.md` — niche trees, query expansion, research depth, time windows, Evidence Ledger, fact-vs-inference, confidence methodology. Read for any research task.
- `references/competition-intelligence.md` — video intelligence, competitor discovery, direct vs adjacent, outlier methodology, demand vs supply vs competitive strength, content-gap detection, winning patterns, opportunity mapping. Read for competitor/video/opportunity work.
- `references/language-market.md` — language vs market, matrix, scorecards, cross-language gaps, transferability, localization, evidence requirements. Read when language/market comparison is relevant.
- `references/research-transparency.md` — mandatory research transparency & evidence disclosure (RESEARCH & EVIDENCE NOTE, EVIDENCE BASIS, source attribution, claim classification, sample-aware language, cross-market caution, report ending). Read before writing any substantive report.
- `references/external-data.md` — optional External Data / Metric Input Layer (supported formats, activation, provenance schema, conflict handling, derived metrics, transparency integration). Read when the user supplies structured data or asks how to provide it.
- `references/market-scanner.md` — decision-support output layer: Niche Market State, Niche Width, Competition Scanner, Language × Market Scanner + Market Map, Micro-Niche Map, Channel Scanner, and the four-option Next-Step Navigation rule (including rendering enforcement). Read to format research findings into scanner-style decision support.
- `references/content-performance-intelligence.md` — Content Performance Intelligence / Success Pattern Mapper / Performance Difference Analyzer: hierarchical category→video model, bidirectional top-down/bottom-up analysis, content taxonomy, performance grouping, feature extraction, success-pattern detection, winners-vs-baseline difference analysis, common-vs-differentiating distinction, Success Ladder/Map/Roadmap (with Success Map Evidence Matrix), Channel/Video/Niche/Category Performance Maps