Orchestra-Research/AI-Research-SKILLs — GitHub trend

FINDING #3767 · UNIT ID 1088558237

Orchestra-Research/AI-Research-SKILLs

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

[ TEX ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0103

ENGAGEMENT0.28

FRESHNESS1.00

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

2% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

31.29

ACCEL

+0.39

RETENTION

90.2%

PEAK 2026-10-11 · FORK-RETENTION 9.1% · 219 STARS / WINDOW

Author Audience

AUDIENCE

2,987

FOLLOWERS

141

OWNER ★

13,525

Engagement Signals

FORKS

955

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 219 / 219 (DIVERSITY 1.00)

Why This Is A Finding

Orchestra-Research/AI-Research-SKILLs собрал 219 звёзд за окно, тогда как у автора всего 141 подписчиков — эффективная аудитория ≈ 2,987. Это даёт surprise-индекс 0.0103 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 9.1% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 61% OF 9747 FINDINGS

#668Eurekaleo/awesome-ai-for-games[ TEX ]0.0291 #1410gavinkhung/machine-learning-visualized[ TEX ]0.015 #1851mikubaka88/CCFA-Skills[ TEX ]0.0114 #2522cs341-illinois/coursebook[ TEX ]0.0078 #4088ysyecust/lecture-to-notes[ TEX ]0.00367

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9747 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00+0.00ABOVE 61%

VELOCITY31.293.57+27.71ABOVE 92%

RETENTION90.2%33.3%+56.9 PPABOVE 98%

FORKS955104+851ABOVE 91%

SURPRISE0.010.01+0.00ABOVE 54%