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

FINDING #497 · 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

SURPRISE0.0222

ENGAGEMENT0.20

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

37.71

ACCEL

-5.25

RETENTION

75.0%

PEAK 2026-07-08 · FORK-RETENTION 0.0% · 264 STARS / WINDOW

Author Audience

AUDIENCE

1,656

FOLLOWERS

263

OWNER ★

13,929

Engagement Signals

FORKS

1,212

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 264 / 264 (DIVERSITY 1.00)

Why This Is A Finding

wanshuiyin/Auto-claude-code-research-in-sleep собрал 264 звёзд за окно, тогда как у автора всего 263 подписчиков — эффективная аудитория ≈ 1,656. Это даёт surprise-индекс 0.0222 (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 56% OF 1120 FINDINGS

#01MDX-Tom/gpt-5.6-instruct[ PYTHON ]0.69 #02Git-creat7/grokRegister-cpa[ PYTHON ]0.58 #03bradautomates/claude-video[ PYTHON ]0.55 #05AlephAITech/WorkBuddyGuide[ PYTHON ]0.51 #06fqscfqj/Y2A-Auto[ PYTHON ]0.49

METRICS IN CONTEXT

MEDIAN ACROSS ALL 1120 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.01+0.00ABOVE 56%

VELOCITY37.7113.86+23.86ABOVE 76%

RETENTION75.0%36.8%+38.2 PPABOVE 92%

FORKS1,21250+1,162ABOVE 88%

SURPRISE0.020.04-0.02ABOVE 34%