google-deepmind/science-skills — GitHub trend

FINDING #5897 · UNIT ID 1237911785

google-deepmind/science-skills

GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.000148

ENGAGEMENT0.20

FRESHNESS1.00

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

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

4% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

13.71

ACCEL

+0.11

RETENTION

72.2%

PEAK 2026-07-09 · FORK-RETENTION 0.0% · 96 STARS / WINDOW

Author Audience

AUDIENCE

92,635

FOLLOWERS

25,546

OWNER ★

207,716

Engagement Signals

FORKS

240

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 96 / 96 (DIVERSITY 1.00)

Why This Is A Finding

google-deepmind/science-skills собрал 96 звёзд за окно, тогда как у автора всего 25,546 подписчиков — эффективная аудитория ≈ 92,635. Это даёт surprise-индекс 0.000148 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 14% OF 6892 FINDINGS

#01MDX-Tom/gpt-5.6-instruct[ PYTHON ]0.86 #02Git-creat7/grokRegister-cpa[ PYTHON ]0.67 #04William-Lu-stack/LuxyAI[ PYTHON ]0.52 #05AlephAITech/WorkBuddyGuide[ PYTHON ]0.51 #06Cjbuilds/Codex-Orchestration[ PYTHON ]0.51

METRICS IN CONTEXT

MEDIAN ACROSS ALL 6892 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 14%

VELOCITY13.714.14+9.57ABOVE 80%

RETENTION72.2%40.6%+31.6 PPABOVE 88%

FORKS24089+151ABOVE 74%

SURPRISE0.000.01-0.01ABOVE 5%