aiwithremy/claude-skills-llm-council — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #8080 · UNIT ID 1221232109

aiwithremy/claude-skills-llm-council

LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review

[ ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0256

ENGAGEMENT0.31

FRESHNESS1.31

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

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

14% OF STARS IN ARCHIVE

[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:

S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS

S7 · THIS REPO IS ~ALL OF THE OWNER'S STARS

S10 · DEAD CODE, ZERO CONTRIBUTORS, YET STARS KEEP DRIPPING

Growth Telemetry

VELOCITY /D

12.10

ACCEL

-0.36

RETENTION

32.3%

PEAK 2026-10-05 · FORK-RETENTION 29.2% · 363 STARS / WINDOW

Author Audience

AUDIENCE

432

FOLLOWERS

156

OWNER ★

2,763

Engagement Signals

FORKS

217

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 363 / 363 (DIVERSITY 1.00)

Why This Is A Finding

aiwithremy/claude-skills-llm-council собрал 363 звёзд за окно, тогда как у автора всего 156 подписчиков — эффективная аудитория ≈ 432. Это даёт surprise-индекс 0.0256 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 29.2% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 16% OF 9675 FINDINGS

#01Niko1221/Strata[ C++ ]0.73 #02Ebony-Vinyl/dsh-our-free-model[ JAVASCRIPT ]0.60 #03BlueHeisenberg/SCSKiller[ C# ]0.54 #04QingYunA/answer-me-with-html[ JAVASCRIPT ]0.51 #05Louis-CFM/coucou[ SWIFT ]0.50

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9675 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 16%

VELOCITY12.103.80+8.30ABOVE 81%

RETENTION32.3%20.3%+12.1 PPABOVE 75%

FORKS217138+79ABOVE 60%

SURPRISE0.030.01+0.02ABOVE 78%