Qwen-Applications/Trace2Skill — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #5622 · UNIT ID 1222295714

Qwen-Applications/Trace2Skill

Official codebase of the paper -- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00825

ENGAGEMENT0.20

FRESHNESS1.35

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

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

27% OF STARS IN ARCHIVE

[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:

S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS

S10 · S10

Growth Telemetry

VELOCITY /D

1.70

ACCEL

-0.05

RETENTION

25.0%

PEAK 2026-06-23 · FORK-RETENTION 0.0% · 51 STARS / WINDOW

Author Audience

AUDIENCE

166

FOLLOWERS

OWNER ★

450

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 51 / 51 (DIVERSITY 1.00)

Why This Is A Finding

Qwen-Applications/Trace2Skill собрал 51 звёзд за окно, тогда как у автора всего 38 подписчиков — эффективная аудитория ≈ 166. Это даёт surprise-индекс 0.00825 (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 11% OF 6295 FINDINGS

#01shy3130/tickflow-stock-panel[ PYTHON ]0.46 #06Panniantong/Agent-Reach[ PYTHON ]0.29 #10sums001/Windows-Copilot-API[ PYTHON ]0.27 #12HUANGCHIHHUNGLeo/claude-real-video[ PYTHON ]0.24 #14realiti4/claude-swap[ PYTHON ]0.21

METRICS IN CONTEXT

MEDIAN ACROSS ALL 6295 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 11%

VELOCITY1.704.23-2.53ABOVE 7%

RETENTION25.0%29.4%-4.4 PPABOVE 41%

FORKS1492-78ABOVE 11%

SURPRISE0.010.01-0.00ABOVE 41%