▲РЕПО НЕТ В ОКНЕ 1D. ПОКАЗАН FINDING ИЗ ОКНА 30D (30 days) — РАНГ #9089.
FINDING #9089 · UNIT ID 1273073712
Spark-To-Paper-Skills/spark-to-paper-skills
One sentence in, one draft paper out: spark-to-paper-skills automatically reviews papers, plans and runs experiments, and writes a research draft—typically using about $10 in API costs per paper.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
15% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S1b · REPO PREDATES ITS OWNER ACCOUNT (TRANSFERRED / RE-CREATED)
S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS
S10 · DEAD CODE, ZERO CONTRIBUTORS, YET STARS KEEP DRIPPING
Growth Telemetry
VELOCITY /D
6.17
ACCEL
-0.47
RETENTION
13.3%
PEAK 2026-10-01 · FORK-RETENTION 0.0% · 185 STARS / WINDOW
Author Audience
AUDIENCE
544
FOLLOWERS
3
OWNER ★
2,690
Engagement Signals
FORKS
21
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 185 / 185 (DIVERSITY 1.00)
Why This Is A Finding
Spark-To-Paper-Skills/spark-to-paper-skills собрал 185 звёзд за окно, тогда как у автора всего 3 подписчиков — эффективная аудитория ≈ 544. Это даёт surprise-индекс 0.0106 (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 6% OF 9675 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9675 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 6%
VELOCITY6.173.80+2.37ABOVE 66%
RETENTION13.3%20.3%-7.0 PPABOVE 33%
FORKS21138-117ABOVE 15%
SURPRISE0.010.01+0.00ABOVE 58%