FINDING #4908 · UNIT ID 1202576122
Aperivue/medsci-skills
Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & GitHub Copilot. Built by a physician-researcher, tested on real publications. MIT.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
81% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS
S5 · PREDATES WINDOW, YET HALF+ OF ALL ITS STARS LANDED IN IT
S7 · THIS REPO IS ~ALL OF THE OWNER'S STARS
Growth Telemetry
VELOCITY /D
1.81
ACCEL
-0.00
RETENTION
19.8%
PEAK 2026-05-13 · FORK-RETENTION 0.0% · 163 STARS / WINDOW
Author Audience
AUDIENCE
72
FOLLOWERS
16
OWNER ★
201
Engagement Signals
FORKS
52
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 163 / 163 (DIVERSITY 1.00)
Why This Is A Finding
Aperivue/medsci-skills собрал 163 звёзд за окно, тогда как у автора всего 16 подписчиков — эффективная аудитория ≈ 72. Это даёт surprise-индекс 0.0161 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.
Related Findings
RANKS ABOVE 23% OF 6380 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 6380 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 23%
VELOCITY1.813.99-2.18ABOVE 12%
RETENTION19.8%17.1%+2.6 PPABOVE 56%
FORKS5290-37ABOVE 34%
SURPRISE0.020.01+0.00ABOVE 58%