Github Trends®
9733 findingsmedian surprise 0.00869window 7 days
UNIT / TREND-MONITOR · REV 2.6
[ 7 days window ]
SOURCE: own snapshots
FINDING #3980 · UNIT ID 1329272295
Leonxlnx/unlazy
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
[ JAVASCRIPT ][ GITHUB ↗ ]
SURPRISE SCORE
0.00

Score Breakdown

SURPRISE0.00799
ENGAGEMENT0.32
FRESHNESS1.00
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
49% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D
81.29
ACCEL
+35.39
RETENTION
0.0%
PEAK 2026-08-22 · FORK-RETENTION 0.0% · 569 STARS / WINDOW

Author Audience

AUDIENCE
10,130
FOLLOWERS
1,728
OWNER ★
84,016

Engagement Signals

FORKS
79
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 569 / 569 (DIVERSITY 1.00)

Why This Is A Finding

Leonxlnx/unlazy собрал 569 звёзд за окно, тогда как у автора всего 1,728 подписчиков — эффективная аудитория ≈ 10,130. Это даёт surprise-индекс 0.00799 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9733 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00+0.00ABOVE 59%
VELOCITY81.293.57+77.71ABOVE 97%
RETENTION0.0%34.4%-34.4 PPABOVE 0%
FORKS7998-19ABOVE 44%
SURPRISE0.010.01-0.00ABOVE 48%