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

FINDING #313 · 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

SURPRISE0.0262

ENGAGEMENT0.20

FRESHNESS1.40

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

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

10% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

44.47

ACCEL

-0.90

RETENTION

50.7%

PEAK 2026-06-15 · FORK-RETENTION 0.0% · 1,334 STARS / WINDOW

Author Audience

AUDIENCE

1,656

FOLLOWERS

263

OWNER ★

13,929

Engagement Signals

FORKS

1,212

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 1,334 / 1,334 (DIVERSITY 1.00)

Why This Is A Finding

wanshuiyin/Auto-claude-code-research-in-sleep собрал 1,334 звёзд за окно, тогда как у автора всего 263 подписчиков — эффективная аудитория ≈ 1,656. Это даёт surprise-индекс 0.0262 (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 69% OF 1013 FINDINGS

#04Panniantong/Agent-Reach[ PYTHON ]0.29 #09tllovesxs/wandao[ PYTHON ]0.22 #11realiti4/claude-swap[ PYTHON ]0.21 #17crazyykhllc-bit/CyberPPT[ PYTHON ]0.17 #22makerspet/oomwoo[ PYTHON ]0.16

METRICS IN CONTEXT

MEDIAN ACROSS ALL 1013 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.01ABOVE 69%

VELOCITY44.477.20+37.27ABOVE 83%

RETENTION50.7%30.8%+19.9 PPABOVE 83%

FORKS1,21256+1,156ABOVE 89%

SURPRISE0.030.03-0.01ABOVE 43%