wanshuiyin/Auto-claude-code-research-in-sleep — GitHub trend

FINDING #2460 · UNIT ID 1177608268

wanshuiyin/Auto-claude-code-research-in-sleep

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.014

ENGAGEMENT0.31

FRESHNESS1.47

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

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

6% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

32.83

ACCEL

-1.22

RETENTION

45.3%

PEAK 2026-09-23 · FORK-RETENTION 58.5% · 985 STARS / WINDOW

Author Audience

AUDIENCE

2,298

FOLLOWERS

387

OWNER ★

19,105

Engagement Signals

FORKS

1,596

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 985 / 985 (DIVERSITY 1.00)

Why This Is A Finding

wanshuiyin/Auto-claude-code-research-in-sleep собрал 985 звёзд за окно, тогда как у автора всего 387 подписчиков — эффективная аудитория ≈ 2,298. Это даёт surprise-индекс 0.014 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 58.5% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 75% OF 9675 FINDINGS

#06NandhaKishorM/laya[ PYTHON ]0.50 #08Oldcircle/geo-sleuth[ PYTHON ]0.45 #09rehan-remade/universal-modder[ PYTHON ]0.44 #17nykooi1/vibe-wise[ PYTHON ]0.32 #23Edwardxlai/easyread[ PYTHON ]0.29

METRICS IN CONTEXT

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

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.01ABOVE 75%

VELOCITY32.833.80+29.03ABOVE 93%

RETENTION45.3%20.3%+25.0 PPABOVE 92%

FORKS1,596138+1,458ABOVE 92%

SURPRISE0.010.01+0.01ABOVE 64%