Outlier Radar

---
name: taffy-outlier-radar
tagline: "See which recent niche videos have the strongest packaging and audience resonance. Add view baselines for true outlier scoring, then choose the format and reference worth acting on next."
description: |
  TRIGGERS: "what's working in my niche", "find the outliers", "scan these channels for breakout videos", "outlier radar", "what should I make to ride the trend", "which competitor video should I model", "what's blowing up in [niche] right now", "rank these videos by packaging". Cadence: weekly.
  NEGATIVE TRIGGERS: Do NOT activate to deconstruct ONE already-chosen video into a script (use taffy-reverse-engineer — outlier-radar finds WHICH video, reverse-engineer turns it into a script). Do NOT activate for the creator's OWN catalog performance (use taffy-content-audit). Do NOT activate for audience-demand ideation from the creator's own comments (use taffy-comment-intelligence). Do NOT run without a candidate video/channel set to scan.
  OUTCOME: A ranked outlier radar for a creator-supplied niche set: each recent video deconstructed by packaging (title pattern, hook, curiosity gap) and comment-resonance signal, one "ride this week" format call, and a shortlist of which videos to reverse-engineer next. Composes Taffy MCP youtube_analyze + youtube_comments_analyze + youtube_transcript, grounds the creator's angle via creator_channel_chat. Chains into taffy-reverse-engineer.
argument-hint: "<comma-separated video URLs/ids> | channel:<url/@handle> [niche or target topic]"
---

# Outlier Radar

You scan a creator-supplied set of recent niche videos, rank their packaging and comment resonance, and tell the creator which format and reference deserve attention next. When the creator also supplies views and normal channel baselines, add true performance-outlier evidence.

The wedge: you deconstruct the *transferable* part — the title pattern, the first-line hook, the curiosity gap — and weight it by how the audience reacted in the comments. Without supplied views, this is a packaging-and-resonance radar, not proof that a video is a performance outlier. Then you point at the one video worth turning into the creator's own script. That last step is `taffy-reverse-engineer`.

## ICP contract

- **The creator wants:** Know which current competitor topic or format deserves attention before committing production time.
- **We promise:** A ranked packaging-and-resonance radar from a creator-supplied recent video set, one creator-specific “ride this week” call, and 1–3 references worth deconstructing.
- **We do not promise:** Automatic channel monitoring, discovery of recent uploads, a true view-multiple outlier score without pasted view/baseline data, causal proof of why a video performed, or guaranteed trend lift.
- **First-run input:** 8–20 recent video URLs across small, mid-sized, and large niche creators; add current views and each channel's normal range for a true outlier ranking.
- **First value:** During onboarding, agree on three competitor channels and run one supplied candidate set against the creator's next-video topic.
- **Thin-data fallback:** Without view baselines, label the output **packaging and comment-resonance radar**, not performance outliers. If the set is stale or homogeneous, ask for a better sample.

## When to invoke

Trigger when the user says any of:
- "what's working in my niche" / "what's blowing up in {niche} right now"
- "find the outliers" / "scan these channels for breakout videos"
- "which competitor video should I model"
- "what should I make to ride the trend"
- "rank these videos by packaging"

Cadence: **weekly**. In fast niches (AI, news, finance) the half-life of a working format is days — a weekly scan is the point. Slower niches can run biweekly.

# ... continues for 72 more lines (Creator Club members only) ...