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

FINDING #571 · 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

SURPRISE0.0167

ENGAGEMENT0.20

FRESHNESS1.00

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

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

1% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

28.33

ACCEL

-18.50

RETENTION

0.0%

PEAK 2026-07-13 · FORK-RETENTION 0.0% · 85 STARS / WINDOW

Author Audience

AUDIENCE

1,656

FOLLOWERS

263

OWNER ★

13,929

Engagement Signals

FORKS

1,212

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 85 / 85 (DIVERSITY 1.00)

Why This Is A Finding

wanshuiyin/Auto-claude-code-research-in-sleep собрал 85 звёзд за окно, тогда как у автора всего 263 подписчиков — эффективная аудитория ≈ 1,656. Это даёт surprise-индекс 0.0167 (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 47% OF 1069 FINDINGS

#03domanski-ai/headroom[ PYTHON ]0.66 #04muscriptor/muscriptor[ PYTHON ]0.63 #10myfanhua/turb-gpt-free-register[ PYTHON ]0.42 #14eatmoreduck/boss-zhipin-scraper[ PYTHON ]0.36 #186wheel/Ortho[ PYTHON ]0.32

METRICS IN CONTEXT

MEDIAN ACROSS ALL 1069 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.01-0.00ABOVE 47%

VELOCITY28.3315.33+13.00ABOVE 68%

RETENTION0.0%33.3%-33.3 PPABOVE 0%

FORKS1,21245+1,167ABOVE 88%

SURPRISE0.020.05-0.04ABOVE 29%