FINDING #8355 · 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
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
2% 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
5.86
ACCEL
-2.39
RETENTION
21.3%
PEAK 2026-10-11 · FORK-RETENTION 0.0% · 41 STARS / WINDOW
Author Audience
AUDIENCE
432
FOLLOWERS
156
OWNER ★
2,763
Engagement Signals
FORKS
217
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 41 / 41 (DIVERSITY 1.00)
Why This Is A Finding
aiwithremy/claude-skills-llm-council собрал 41 звёзд за окно, тогда как у автора всего 156 подписчиков — эффективная аудитория ≈ 432. Это даёт surprise-индекс 0.0124 (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 13% OF 9651 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9651 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 13%
VELOCITY5.863.14+2.71ABOVE 70%
RETENTION21.3%16.7%+4.6 PPABOVE 56%
FORKS217277-60ABOVE 46%
SURPRISE0.010.00+0.01ABOVE 72%