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

FINDING #2711 · 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

SURPRISE0.0169

ENGAGEMENT0.29

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

38.71

ACCEL

-5.29

RETENTION

0.0%

PEAK 2026-10-11 · FORK-RETENTION 0.0% · 271 STARS / WINDOW

Author Audience

AUDIENCE

2,254

FOLLOWERS

377

OWNER ★

18,818

Engagement Signals

FORKS

1,459

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 271 / 271 (DIVERSITY 1.00)

Why This Is A Finding

wanshuiyin/Auto-claude-code-research-in-sleep собрал 271 звёзд за окно, тогда как у автора всего 377 подписчиков — эффективная аудитория ≈ 2,254. Это даёт surprise-индекс 0.0169 (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 72% OF 9747 FINDINGS

#06rehan-remade/universal-modder[ PYTHON ]0.81 #10ardeyouxipianyi/workbuddy2api-hub[ PYTHON ]0.62 #19zhongerxin/iPhone-use[ PYTHON ]0.51 #28ithtelab/workbuddy-manager[ PYTHON ]0.38 #35StayLameBro/backburner[ PYTHON ]0.35

METRICS IN CONTEXT

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

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.00ABOVE 72%

VELOCITY38.713.57+35.14ABOVE 94%

RETENTION0.0%33.3%-33.3 PPABOVE 0%

FORKS1,459104+1,355ABOVE 94%

SURPRISE0.020.01+0.01ABOVE 66%