Breakout Detector

Breakout Detector

Big accounts get big numbers on everything — that is baseline, not signal. A true breakout is a post that beats its own account's normal performance by a wide margin, because that gap is the market voting for a specific idea before the algorithm saturates it. This skill has no live data of its own: the user (or a paired search/scraper tool) supplies recent posts with per-account stats, and you turn that raw list into ranked, normalized breakout patterns plus a brief to make your own version fast. Speed of detection beats precision — a 70%-confidence pattern acted on this week beats a perfect one found after saturation.

1. Gather and normalize

1. Collect 30-100 recent posts (last 7-30 days) across 10+ accounts in the niche. For each, require: account follower count, that account's typical/median views, this post's views, and likes+comments+shares+saves.
2. Compute the Outlier Score two ways and keep the higher:

• View Multiple = post views ÷ that account's median views (best signal; needs per-account baseline).
• Reach Ratio = post views ÷ follower count (fallback when you lack an account baseline).

1. Flag as breakout candidate if View Multiple ≥ 3x OR Reach Ratio ≥ 5x. Discard anything under 2x — it's baseline.
2. Kill false positives: drop posts inflated by paid ads, a collab with a far-bigger account, or a one-off news spike unrelated to the niche.

2. Isolate the driver

For each candidate, name the ONE variable most responsible. Score every candidate across:

1. Format — carousel, talking-head, green-screen, listicle, B-roll voiceover, text-on-screen.
2. Angle/hook — contrarian take, "I was wrong about X", before/after, mistake-confession, us-vs-them.
3. Sound/audio — trending sound ID, original VO, specific song. Note if the same sound repeats across candidates.
4. Structure — hook | Window: | Posts analyzed:

TOP BREAKOUT PATTERNS (ranked)

1. — Driver:

Evidence: accounts, avg outlier score, e.g. @acct 8.2x Score: Novelty /5 × Demand /5 × Fit /5 = _/125 Why it's spiking:

MAKE-YOUR-VERSION BRIEF (pattern #1)

• Hook (first 2s):
• Format/shot list:
• Sound/audio:
• Your angle twist:
• Ship-by:

SKIP LIST:

## Platform variants
- **TikTok/Reels/Shorts**: View Multiple is king; watch sounds — a shared trending sound across candidates is the strongest early signal. Saturation window is 3-10 days.
- **YouTube**: use views ÷ channel median and outlier thumbnails/titles; breakouts live longer (weeks), so novelty decays slower.
- **X/Threads**: use impressions ÷ follower count; driver is usually angle/hook, not format. Decay is hours.
- **LinkedIn/Instagram feed**: saves and shares outweigh likes; normalize on those.

## Rules
- Never rank by raw views or follower count — always normalize to the account's own baseline, or you'll just rediscover big accounts.
- A pattern needs 3+ independent accounts hitting outlier scores; one hit is noise.
- Detect the driver, not the topic — copying the topic saturates; copying the format/angle transfers.
- Act inside the saturation window (days, not weeks) or the edge is gone — favor speed over a perfect read.
- Always add a twist so your version isn't a clone; the algorithm punishes duplicates.
- Demand you get fresh input data each run — this skill scores what it's fed and never claims live knowledge.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [moses607](https://github.com/moses607)
- **Source:** [moses607/socialforge](https://github.com/moses607/socialforge)
- **License:** MIT

Install and usage instructions live in the source repository linked above.