FINDING #846 · 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.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
1% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
1.50
ACCEL
-0.13
RETENTION
12.0%
PEAK 2026-09-13 · FORK-RETENTION 20.0% · 45 STARS / WINDOW
Author Audience
AUDIENCE
12,416
FOLLOWERS
2,214
OWNER ★
102,019
Engagement Signals
FORKS
288
ISSUE AUTH
0
PR AUTH
1
UNIQUE STARGAZERS 45 / 45 (DIVERSITY 1.00)
Why This Is A Finding
Leonxlnx/unlazy собрал 45 звёзд за окно, тогда как у автора всего 2,214 подписчиков — эффективная аудитория ≈ 12,416. Это даёт surprise-индекс 0.00012 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 20.0% и 1 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.
Related Findings
RANKS ABOVE 23% OF 1105 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 1105 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 23%
VELOCITY1.502.80-1.30ABOVE 0%
RETENTION12.0%9.4%+2.6 PPABOVE 67%
FORKS2881,173-885ABOVE 27%
SURPRISE0.000.00-0.00ABOVE 19%